Files
Sera-4.6-Lite-T2-v4-1000-ax…/debug.log

15963 lines
2.5 MiB
Plaintext
Raw Normal View History

[2026-04-23 04:55:06,854] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:2005626] bf16 support detected, enabling for this configuration.
[2026-04-23 04:55:06,954] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:2005626] baseline 0.000GB ()
[2026-04-23 04:55:06,954] [INFO] [axolotl.cli.config.load_cfg:341] [PID:2005626] config:
{
"activation_offloading": true,
"adam_beta1": 0.9,
"adam_beta2": 0.95,
"axolotl_config_path": "/e/scratch/jureap59/feuer1/code/axolotl_configs/qwen3_8b_sera_v4_1000.yaml",
"base_model": "Qwen/Qwen3-8B",
"base_model_config": "Qwen/Qwen3-8B",
"batch_size": 32,
"bf16": true,
"capabilities": {
"bf16": true,
"compute_capability": "sm_90",
"fp8": true,
"n_gpu": 4,
"n_node": 1,
"tf32": true
},
"chat_template": "chatml",
"context_parallel_size": 1,
"dataloader_num_workers": 4,
"dataloader_pin_memory": true,
"dataloader_prefetch_factor": 256,
"dataset_num_proc": 288,
"dataset_prepared_path": "/e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000",
"datasets": [
{
"chat_template": "tokenizer_default",
"data_files": [
"sera-4.6-lite-t2_v4_1000.jsonl"
],
"ds_type": "json",
"field_messages": "messages",
"message_field_training": "train",
"message_property_mappings": {
"content": "content",
"role": "role"
},
"path": "laion/Sera-4.6-Lite-T2-v4-1000",
"trust_remote_code": false,
"type": "chat_template"
}
],
"ddp": true,
"deepspeed": {
"bf16": {
"enabled": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false,
"zero_optimization": {
"contiguous_gradients": true,
"gather_16bit_weights_on_model_save": true,
"max_live_parameters": 0,
"max_reuse_distance": 0,
"overlap_comm": true,
"reduce_bucket_size": "auto",
"stage": 3,
"stage3_param_persistence_threshold": "auto",
"stage3_prefetch_bucket_size": "auto",
"sub_group_size": 0
}
},
"device": "cuda:0",
"device_map": {
"": 0
},
"dion_rank_fraction": 1.0,
"dion_rank_multiple_of": 1,
"eaft_alpha": 1.0,
"eaft_k": 20,
"env_capabilities": {
"torch_version": "2.9.1"
},
"eval_batch_size": 1,
"eval_causal_lm_metrics": [
"sacrebleu",
"comet",
"ter",
"chrf"
],
"eval_max_new_tokens": 128,
"eval_table_size": 0,
"evals_per_epoch": 0,
"experimental_skip_move_to_device": true,
"flash_attention": true,
"fp16": false,
"generate_samples": false,
"generation_do_sample": true,
"generation_max_new_tokens": 50,
"generation_prompt_ratio": 0.5,
"generation_temperature": 0.7,
"gradient_accumulation_steps": 8,
"gradient_checkpointing": true,
"gradient_checkpointing_kwargs": {
"use_reentrant": true
},
"include_tkps": true,
"layer_offloading": false,
"learning_rate": 1e-05,
"lisa_layers_attribute": "model.layers",
"load_best_model_at_end": false,
"load_in_4bit": false,
"load_in_8bit": false,
"local_rank": 0,
"logging_steps": 1,
"lora_dropout": 0.0,
"loraplus_lr_embedding": 1e-06,
"loss_watchdog_patience": 3,
"loss_watchdog_threshold": 5.0,
"lr_scheduler": "cosine",
"max_grad_norm": 1.0,
"mean_resizing_embeddings": false,
"merge_method": "memory_efficient",
"micro_batch_size": 1,
"model_config_type": "qwen3",
"num_epochs": 3.0,
"num_generation_samples": 3,
"optimizer": "adamw_torch",
"otel_metrics_host": "localhost",
"otel_metrics_port": 8000,
"output_dir": "/e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B",
"pretrain_multipack_attn": true,
"profiler_steps_start": 0,
"qlora_sharded_model_loading": false,
"quantize_moe_experts": false,
"ray_num_workers": 1,
"resources_per_worker": {
"GPU": 1
},
"sample_packing_bin_size": 200,
"sample_packing_group_size": 100000,
"save_only_model": false,
"save_safetensors": true,
"save_strategy": "epoch",
"sequence_len": 32768,
"shuffle_before_merging_datasets": false,
"shuffle_merged_datasets": true,
"skip_prepare_dataset": false,
"streaming_multipack_buffer_size": 10000,
"strict": false,
"tensor_parallel_size": 1,
"tf32": false,
"tiled_mlp_use_original_mlp": true,
"tokenizer_config": "Qwen/Qwen3-8B",
"tokenizer_save_jinja_files": true,
"torch_dtype": "torch.bfloat16",
"train_on_inputs": false,
"trl": {
"async_prefetch": false,
"log_completions": false,
"mask_truncated_completions": false,
"ref_model_mixup_alpha": 0.9,
"ref_model_sync_steps": 64,
"replay_buffer_size": 0,
"replay_recompute_logps": true,
"reroll_max_groups": 1,
"reroll_start_fraction": 1.0,
"reward_num_workers": 1,
"scale_rewards": true,
"skip_zero_advantage_batches": true,
"sync_ref_model": false,
"use_data_producer": false,
"use_vllm": false,
"vllm_lora_sync": false,
"vllm_server_host": "0.0.0.0",
"vllm_server_port": 8000
},
"use_otel_metrics": false,
"use_ray": false,
"val_set_size": 0.0,
"vllm": {
"device": "auto",
"dtype": "auto",
"gpu_memory_utilization": 0.9,
"host": "0.0.0.0",
"port": 8000
},
"wandb_name": "sera-v4-1000-axolotl__Qwen3-8B",
"warmup_ratio": 0.1875,
"weight_decay": 0.01,
"world_size": 4
}
[2026-04-23 04:55:06,969] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:2005626] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.
[2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:2005626] EOS: 151645 / <|im_end|>
[2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:2005626] BOS: None / None
[2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:2005626] PAD: 151643 / <|endoftext|>
[2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:2005626] UNK: None / None
[2026-04-23 04:55:07,655] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:2005626] Loading prepared dataset from disk at /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000/76673564c8e541b3c5479d2bc430da04...
[2026-04-23 04:55:07,784] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:2005626] total_num_tokens: 13_352_339
[2026-04-23 04:55:07,940] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:2005626] `total_supervised_tokens: 4_727_034`
[2026-04-23 04:55:07,940] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:2005626] total_num_steps: 54
[2026-04-23 04:55:07,940] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:2005626] Maximum number of steps set at 54
[2026-04-23 04:55:07,977] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:2005626] loading tokenizer... Qwen/Qwen3-8B
[2026-04-23 04:55:08,231] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:2005626] EOS: 151645 / <|im_end|>
[2026-04-23 04:55:08,232] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:2005626] BOS: None / None
[2026-04-23 04:55:08,232] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:2005626] PAD: 151643 / <|endoftext|>
[2026-04-23 04:55:08,232] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:2005626] UNK: None / None
[2026-04-23 04:55:08,232] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:2005626] Loading model
[2026-04-23 04:55:08,302] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:2005626] Patched Trainer.evaluation_loop with nanmean loss calculation
[2026-04-23 04:55:08,303] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:2005626] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
[2026-04-23 04:55:09,008] [INFO] [axolotl.monkeypatch.attention.flash_attn_4.patch_flash_attn_4:52] [PID:2005626] Flash Attention 4 is available for your GPU and offers faster training speeds. To enable: pip install flash-attn-4
[2026-04-23 04:55:09,009] [INFO] [axolotl.monkeypatch.deepspeed_utils.patch_checkpoint_wrapper_setattr:52] [PID:2005626] CheckpointWrapper patched to forward DeepSpeed attributes
[2026-04-23 04:55:47,184] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:2005626] Converting modules to torch.bfloat16
[2026-04-23 04:55:47,187] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:2005626] Memory usage after model load 4.973GB (+4.973GB allocated, +5.080GB reserved)
[2026-04-23 04:55:53,788] [INFO] [axolotl.train.save_initial_configs:421] [PID:2005626] Pre-saving tokenizer to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B...
[2026-04-23 04:55:53,869] [INFO] [axolotl.train.save_initial_configs:426] [PID:2005626] Pre-saving model config to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B...
[2026-04-23 04:55:53,872] [INFO] [axolotl.train.execute_training:222] [PID:2005626] Starting trainer...
[2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:54,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer
0%| | 0/54 [00:00<?, ?it/s][2026-04-23 04:55:57,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:58,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:55:59,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:06,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:07,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:08,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:08,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:08,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:08,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:08,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:08,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:19,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:20,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:21,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:21,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:21,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:21,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:32,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:33,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:34,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:43,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:44,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:52,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:53,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:56:54,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:01,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:01,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:02,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:03,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:04,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:12,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:13,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:14,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
2%|▏ | 1/54 [01:30<1:20:22, 91.00s/it] {'loss': '0.6551', 'grad_norm': '12.13', 'learning_rate': '0', 'ppl': '1.925', 'memory/max_active (GiB)': '76.03', 'memory/max_allocated (GiB)': '74.56', 'memory/device_reserved (GiB)': '88.16', 'tokens/train_per_sec_per_gpu': '105.7', 'tokens/total': 761664, 'tokens/trainable': 265152, 'epoch': '0.05556'}
2%|▏ | 1/54 [01:30<1:20:22, 91.00s/it][2026-04-23 04:57:26,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:26,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:26,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:26,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:26,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:26,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:26,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:27,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:28,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:37,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:38,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:39,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:39,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:39,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:39,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:48,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:49,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:50,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:58,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:57:59,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:00,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:00,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:06,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:06,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:06,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:06,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:06,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:07,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:08,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:17,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:18,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:19,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:28,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:29,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:34,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:35,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:36,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:45,355] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
4%|▎ | 2/54 [02:49<1:12:36, 83.78s/it] {'loss': '0.6268', 'grad_norm': '11.41', 'learning_rate': '1e-06', 'ppl': '1.872', 'memory/max_active (GiB)': '86.28', 'memory/max_allocated (GiB)': '86.28', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '117.1', 'tokens/total': 1518720, 'tokens/trainable': 528754, 'epoch': '0.1111'}
4%|▎ | 2/54 [02:49<1:12:36, 83.78s/it][2026-04-23 04:58:45,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:45,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:45,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:45,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:45,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:46,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:47,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:48,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:48,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:48,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:48,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:48,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:48,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:57,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:58:58,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:04,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:04,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:05,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:06,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:14,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:15,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:16,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:26,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:27,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:28,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:37,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:38,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:45,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:46,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:47,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:56,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:56,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:56,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:56,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:56,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:56,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:57,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 04:59:58,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,412] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
6%|▌ | 3/54 [04:12<1:10:55, 83.45s/it] {'loss': '0.6181', 'grad_norm': '10.92', 'learning_rate': '2e-06', 'ppl': '1.855', 'memory/max_active (GiB)': '91.71', 'memory/max_allocated (GiB)': '91.71', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '111.5', 'tokens/total': 2286528, 'tokens/trainable': 815214, 'epoch': '0.1667'}
6%|▌ | 3/54 [04:12<1:10:55, 83.45s/it][2026-04-23 05:00:08,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:08,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:09,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:10,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:11,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:11,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:11,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:11,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:11,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:20,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:21,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:22,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:33,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:34,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:35,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:35,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:42,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:42,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:42,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:43,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:44,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:54,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:55,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:00:56,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:03,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:04,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:14,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:15,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:16,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:25,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:26,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:27,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:27,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:27,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,641] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
7%|▋ | 4/54 [05:42<1:11:26, 85.73s/it] {'loss': '0.619', 'grad_norm': '10.57', 'learning_rate': '3e-06', 'ppl': '1.857', 'memory/max_active (GiB)': '85.32', 'memory/max_allocated (GiB)': '85.32', 'memory/device_reserved (GiB)': '92.83', 'tokens/train_per_sec_per_gpu': '105.8', 'tokens/total': 3070912, 'tokens/trainable': 1092163, 'epoch': '0.2222'}
7%|▋ | 4/54 [05:42<1:11:26, 85.73s/it][2026-04-23 05:01:37,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:37,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:38,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:39,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:40,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:48,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:48,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:48,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:48,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:48,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:49,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:01:50,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:00,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:01,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:10,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:11,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:12,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:12,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:12,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:12,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:12,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:21,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:22,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:23,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:32,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:33,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:40,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:41,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:42,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:42,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:42,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:48,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:48,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:48,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:48,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:48,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:49,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:02:50,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,454] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
9%|▉ | 5/54 [07:04<1:09:09, 84.68s/it] {'loss': '0.5333', 'grad_norm': '7.206', 'learning_rate': '4e-06', 'ppl': '1.704', 'memory/max_active (GiB)': '87.81', 'memory/max_allocated (GiB)': '87.81', 'memory/device_reserved (GiB)': '90.31', 'tokens/train_per_sec_per_gpu': '102.1', 'tokens/total': 3804672, 'tokens/trainable': 1352000, 'epoch': '0.2778'}
9%|▉ | 5/54 [07:04<1:09:09, 84.68s/it][2026-04-23 05:03:00,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:00,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:01,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:07,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:07,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:07,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:07,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:07,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:07,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:08,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:09,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:10,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:10,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:18,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:18,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:18,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:18,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:18,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:18,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:19,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:20,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:29,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:29,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:29,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:30,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:31,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:32,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:41,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:42,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:43,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:43,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:51,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:03:52,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:02,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:03,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:04,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:04,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:04,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:04,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:13,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:14,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:15,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,021] [WARNING] [stage3.py:2497:step] 11 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
11%|█ | 6/54 [08:29<1:07:42, 84.64s/it] {'loss': '0.4688', 'grad_norm': '3.423', 'learning_rate': '5e-06', 'ppl': '1.598', 'memory/max_active (GiB)': '91.59', 'memory/max_allocated (GiB)': '91.59', 'memory/device_reserved (GiB)': '92.85', 'tokens/train_per_sec_per_gpu': '99.47', 'tokens/total': 4488832, 'tokens/trainable': 1594112, 'epoch': '0.3333'}
11%|█ | 6/54 [08:29<1:07:42, 84.64s/it][2026-04-23 05:04:25,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:25,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:26,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:34,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:35,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:36,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:44,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:45,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:54,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:04:55,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:01,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:02,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:03,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:11,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:12,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:13,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:23,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:24,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:25,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:34,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:35,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:36,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:45,691] [WARNING] [stage3.py:2497:step] 1 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
13%|█▎ | 7/54 [09:50<1:05:17, 83.34s/it] {'loss': '0.443', 'grad_norm': '2.656', 'learning_rate': '6e-06', 'ppl': '1.557', 'memory/max_active (GiB)': '81.18', 'memory/max_allocated (GiB)': '80.02', 'memory/device_reserved (GiB)': '91.85', 'tokens/train_per_sec_per_gpu': '130.8', 'tokens/total': 5198016, 'tokens/trainable': 1846440, 'epoch': '0.3889'}
13%|█▎ | 7/54 [09:50<1:05:17, 83.34s/it][2026-04-23 05:05:45,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:45,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:45,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:45,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:45,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:45,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:46,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:47,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:54,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:54,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:55,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:05:56,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:05,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:05,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:05,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:05,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:06,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:07,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:14,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:15,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:16,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:24,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:25,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:26,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:26,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:35,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:36,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:37,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:46,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:47,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:48,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:48,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:48,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:48,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:56,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:57,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:06:58,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,358] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
15%|█▍ | 8/54 [11:12<1:03:43, 83.13s/it] {'loss': '0.4107', 'grad_norm': '3.69', 'learning_rate': '7e-06', 'ppl': '1.508', 'memory/max_active (GiB)': '90.17', 'memory/max_allocated (GiB)': '90.17', 'memory/device_reserved (GiB)': '92.83', 'tokens/train_per_sec_per_gpu': '83.57', 'tokens/total': 5897984, 'tokens/trainable': 2093107, 'epoch': '0.4444'}
15%|█▍ | 8/54 [11:12<1:03:43, 83.13s/it][2026-04-23 05:07:08,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:08,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:09,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:10,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:19,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:20,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:21,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:31,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:32,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:33,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:42,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:43,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:44,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:54,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:07:55,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:01,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:02,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:03,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:11,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:12,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:13,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:21,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:22,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,028] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
17%|█▋ | 9/54 [12:33<1:01:46, 82.36s/it] {'loss': '0.3983', 'grad_norm': '1.607', 'learning_rate': '8e-06', 'ppl': '1.489', 'memory/max_active (GiB)': '87.58', 'memory/max_allocated (GiB)': '87.58', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '82.26', 'tokens/total': 6647808, 'tokens/trainable': 2352829, 'epoch': '0.5'}
17%|█▋ | 9/54 [12:33<1:01:46, 82.36s/it][2026-04-23 05:08:29,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:29,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:30,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:31,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:39,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:40,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:41,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:41,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:41,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:41,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:41,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:41,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:51,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:51,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:51,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:51,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:51,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:51,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:52,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:53,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:59,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:08:59,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:00,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:01,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:10,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:11,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:18,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:19,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:20,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:29,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:30,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:31,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:31,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:39,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:39,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:39,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:40,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:41,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:51,959] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
19%|█▊ | 10/54 [13:56<1:00:31, 82.54s/it] {'loss': '0.3369', 'grad_norm': '1.341', 'learning_rate': '9e-06', 'ppl': '1.401', 'memory/max_active (GiB)': '92.06', 'memory/max_allocated (GiB)': '92.06', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '119.9', 'tokens/total': 7396288, 'tokens/trainable': 2645188, 'epoch': '0.5556'}
19%|█▊ | 10/54 [13:56<1:00:31, 82.54s/it][2026-04-23 05:09:51,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:52,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:09:53,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:01,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:02,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:10,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:10,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:10,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:10,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:10,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:10,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:11,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:12,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:21,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:22,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:23,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:23,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:23,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:23,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:30,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:31,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:32,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:41,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:41,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:41,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:41,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:41,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:42,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:43,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:53,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:54,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:55,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:55,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:55,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:10:55,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:03,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:04,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:05,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:05,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:05,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:05,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:05,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:05,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,469] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
20%|██ | 11/54 [15:17<58:55, 82.22s/it] {'loss': '0.3025', 'grad_norm': '0.8523', 'learning_rate': '1e-05', 'ppl': '1.353', 'memory/max_active (GiB)': '89.23', 'memory/max_allocated (GiB)': '89.23', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '98.62', 'tokens/total': 8149824, 'tokens/trainable': 2916548, 'epoch': '0.6111'}
20%|██ | 11/54 [15:17<58:55, 82.22s/it][2026-04-23 05:11:13,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:13,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:14,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:15,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:24,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:25,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:26,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:37,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:38,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:39,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:39,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:39,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:39,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:39,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:48,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:48,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:49,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:50,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:51,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:51,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:11:51,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:02,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:03,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:04,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:12,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:13,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:14,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:20,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:21,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:22,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:31,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:31,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:31,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:32,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:33,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,438] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
22%|██▏ | 12/54 [16:46<58:59, 84.27s/it] {'loss': '0.3254', 'grad_norm': '0.6262', 'learning_rate': '9.987e-06', 'ppl': '1.385', 'memory/max_active (GiB)': '89.46', 'memory/max_allocated (GiB)': '89.46', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '106.8', 'tokens/total': 8969920, 'tokens/trainable': 3205374, 'epoch': '0.6667'}
22%|██▏ | 12/54 [16:46<58:59, 84.27s/it][2026-04-23 05:12:42,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:42,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:43,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:44,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:51,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:51,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:52,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:53,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:12:59,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:00,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:01,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:01,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:01,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:10,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:11,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:16,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:17,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:22,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:23,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:24,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:33,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:34,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:35,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:35,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:35,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:35,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:46,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:47,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,129] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
24%|██▍ | 13/54 [17:59<55:11, 80.77s/it] {'loss': '0.3233', 'grad_norm': '0.6207', 'learning_rate': '9.949e-06', 'ppl': '1.382', 'memory/max_active (GiB)': '85.57', 'memory/max_allocated (GiB)': '85.57', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '104', 'tokens/total': 9667648, 'tokens/trainable': 3449910, 'epoch': '0.7222'}
24%|██▍ | 13/54 [17:59<55:11, 80.77s/it][2026-04-23 05:13:55,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:55,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:13:56,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:02,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:03,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:04,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:04,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:04,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:04,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:04,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:04,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:14,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:15,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:16,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:24,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:25,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:26,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:33,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:34,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:35,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:46,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:47,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:48,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:48,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:48,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:56,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:56,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:56,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:56,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:57,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:58,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:14:59,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:07,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:08,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:09,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:17,963] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
26%|██▌ | 14/54 [19:22<54:15, 81.39s/it] {'loss': '0.2933', 'grad_norm': '0.6171', 'learning_rate': '9.886e-06', 'ppl': '1.341', 'memory/max_active (GiB)': '86.4', 'memory/max_allocated (GiB)': '86.4', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '92.09', 'tokens/total': 10438400, 'tokens/trainable': 3708255, 'epoch': '0.7778'}
26%|██▌ | 14/54 [19:22<54:15, 81.39s/it][2026-04-23 05:15:17,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:18,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:19,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:20,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:20,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:28,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:29,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:35,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:36,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:37,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:37,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:37,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:37,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:37,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:37,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:45,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:46,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:52,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:53,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:54,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:54,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:15:54,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:01,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:02,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:08,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:09,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:10,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:18,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:19,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:20,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,586] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
28%|██▊ | 15/54 [20:34<51:11, 78.75s/it] {'loss': '0.2942', 'grad_norm': '0.5358', 'learning_rate': '9.797e-06', 'ppl': '1.342', 'memory/max_active (GiB)': '83.42', 'memory/max_allocated (GiB)': '83.42', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '127.5', 'tokens/total': 11141120, 'tokens/trainable': 3952215, 'epoch': '0.8333'}
28%|██▊ | 15/54 [20:34<51:11, 78.75s/it][2026-04-23 05:16:30,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:30,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:31,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:32,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:40,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:41,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:47,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:48,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:56,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:57,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:58,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:16:58,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:06,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:06,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:06,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:06,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:06,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:06,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:07,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:08,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:17,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:18,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:27,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:28,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:29,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:39,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:40,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:41,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,310] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
30%|██▉ | 16/54 [21:55<50:15, 79.34s/it] {'loss': '0.2797', 'grad_norm': '0.465', 'learning_rate': '9.685e-06', 'ppl': '1.323', 'memory/max_active (GiB)': '83.33', 'memory/max_allocated (GiB)': '83.33', 'memory/device_reserved (GiB)': '92.79', 'tokens/train_per_sec_per_gpu': '83.07', 'tokens/total': 11905920, 'tokens/trainable': 4216315, 'epoch': '0.8889'}
30%|██▉ | 16/54 [21:55<50:15, 79.34s/it][2026-04-23 05:17:51,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:51,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:52,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:53,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:53,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:53,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:17:53,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:01,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:02,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:12,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:13,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:21,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:22,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:28,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:29,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:36,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:37,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:44,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:44,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:44,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:44,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:44,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:45,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:46,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:56,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:57,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:58,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:58,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:58,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:58,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:58,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:18:58,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:08,935] [WARNING] [stage3.py:2497:step] 4 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
31%|███▏ | 17/54 [23:13<48:36, 78.83s/it] {'loss': '0.2516', 'grad_norm': '0.4703', 'learning_rate': '9.548e-06', 'ppl': '1.286', 'memory/max_active (GiB)': '92.07', 'memory/max_allocated (GiB)': '92.07', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '124.1', 'tokens/total': 12648768, 'tokens/trainable': 4481284, 'epoch': '0.9444'}
31%|███▏ | 17/54 [23:13<48:36, 78.83s/it][2026-04-23 05:19:08,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:09,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:10,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:11,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:11,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:11,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:11,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:18,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:19,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:20,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:30,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:31,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:39,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:40,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:48,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:48,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:49,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:50,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:56,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:56,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:56,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:56,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:56,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:57,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:19:58,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:06,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:06,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:06,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:07,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:08,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:09,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:09,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:17,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:17,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:17,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:18,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:19,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:29,246] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
33%|███▎ | 18/54 [24:33<47:33, 79.27s/it] {'loss': '0.2501', 'grad_norm': '0.4142', 'learning_rate': '9.388e-06', 'ppl': '1.284', 'memory/max_active (GiB)': '87.34', 'memory/max_allocated (GiB)': '87.34', 'memory/device_reserved (GiB)': '92.16', 'tokens/train_per_sec_per_gpu': '120.4', 'tokens/total': 13393728, 'tokens/trainable': 4735708, 'epoch': '1'}
33%|███▎ | 18/54 [24:33<47:33, 79.27s/it][2026-04-23 05:20:31,454] [INFO] [axolotl.core.trainers.base._save:741] [PID:2005626] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B/checkpoint-18
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.79s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.79s/it]
[2026-04-23 05:20:58,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:58,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:20:59,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:00,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:09,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:10,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:19,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:20,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:21,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:21,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:21,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:28,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:29,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:30,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:30,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:30,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:38,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:39,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:40,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:50,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:51,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:21:52,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:01,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:02,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:03,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:13,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:14,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:15,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,333] [WARNING] [stage3.py:2497:step] 8 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
35%|███▌ | 19/54 [26:28<52:31, 90.03s/it] {'loss': '0.261', 'grad_norm': '0.402', 'learning_rate': '9.206e-06', 'ppl': '1.298', 'memory/max_active (GiB)': '91.59', 'memory/max_allocated (GiB)': '91.59', 'memory/device_reserved (GiB)': '92.82', 'tokens/train_per_sec_per_gpu': '94.41', 'tokens/total': 14147968, 'tokens/trainable': 5001854, 'epoch': '1.056'}
35%|███▌ | 19/54 [26:28<52:31, 90.03s/it][2026-04-23 05:22:24,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:24,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:25,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:26,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:35,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:36,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:37,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:48,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:49,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:22:50,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:02,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:02,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:02,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:02,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:03,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:04,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:11,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:12,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:21,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:22,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:23,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:33,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:34,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:35,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:35,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:35,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:35,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:35,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:44,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:44,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:44,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:44,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:44,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:44,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:45,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:46,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:47,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,631] [WARNING] [stage3.py:2497:step] 8 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
37%|███▋ | 20/54 [28:01<51:24, 90.71s/it] {'loss': '0.236', 'grad_norm': '0.3587', 'learning_rate': '9.003e-06', 'ppl': '1.266', 'memory/max_active (GiB)': '92.18', 'memory/max_allocated (GiB)': '92.18', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '124.1', 'tokens/total': 14979264, 'tokens/trainable': 5297490, 'epoch': '1.111'}
37%|███▋ | 20/54 [28:01<51:24, 90.71s/it][2026-04-23 05:23:56,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:56,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:57,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:23:58,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:07,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:08,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:09,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:09,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:16,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:16,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:16,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:16,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:17,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:18,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:18,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:18,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:18,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:18,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:18,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:23,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:23,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:23,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:23,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:24,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:25,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:25,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:25,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:29,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:29,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:29,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:30,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:31,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:31,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:31,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:31,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:31,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:31,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:36,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:37,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:38,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:47,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:47,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:47,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:47,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:48,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:49,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:50,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:24:50,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:00,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:01,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,033] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
39%|███▉ | 21/54 [29:16<47:21, 86.11s/it] {'loss': '0.2403', 'grad_norm': '0.4317', 'learning_rate': '8.779e-06', 'ppl': '1.272', 'memory/max_active (GiB)': '91.82', 'memory/max_allocated (GiB)': '91.82', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '143.3', 'tokens/total': 15687296, 'tokens/trainable': 5562329, 'epoch': '1.167'}
39%|███▉ | 21/54 [29:16<47:21, 86.11s/it][2026-04-23 05:25:12,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:12,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:13,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:14,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:14,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:14,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:14,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:14,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:23,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:24,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:33,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:34,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:41,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:42,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:43,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:51,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:52,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:25:53,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:00,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:01,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:02,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:02,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:02,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:11,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:11,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:11,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:11,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:11,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:11,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:12,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:13,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:23,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:24,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,154] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
41%|████ | 22/54 [30:37<45:07, 84.62s/it] {'loss': '0.2322', 'grad_norm': '0.3557', 'learning_rate': '8.536e-06', 'ppl': '1.261', 'memory/max_active (GiB)': '89.25', 'memory/max_allocated (GiB)': '89.25', 'memory/device_reserved (GiB)': '92.28', 'tokens/train_per_sec_per_gpu': '89.86', 'tokens/total': 16416064, 'tokens/trainable': 5816710, 'epoch': '1.222'}
41%|████ | 22/54 [30:37<45:07, 84.62s/it][2026-04-23 05:26:33,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:33,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:34,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:35,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:44,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:45,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:46,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:56,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:26:57,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:04,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:05,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:06,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:06,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:06,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:06,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:06,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:06,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:15,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:16,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:17,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:26,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:27,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:28,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:36,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:37,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:44,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:45,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:46,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,230] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
43%|████▎ | 23/54 [32:00<43:28, 84.15s/it] {'loss': '0.2059', 'grad_norm': '0.3179', 'learning_rate': '8.274e-06', 'ppl': '1.229', 'memory/max_active (GiB)': '89.11', 'memory/max_allocated (GiB)': '89.11', 'memory/device_reserved (GiB)': '92.69', 'tokens/train_per_sec_per_gpu': '110.4', 'tokens/total': 17166080, 'tokens/trainable': 6078562, 'epoch': '1.278'}
43%|████▎ | 23/54 [32:00<43:28, 84.15s/it][2026-04-23 05:27:56,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:56,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:57,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:27:58,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:09,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:10,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:17,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:18,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:19,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:20,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:29,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:30,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:34,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:35,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:36,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:44,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:45,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:46,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:53,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:54,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:55,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:55,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:28:55,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:02,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:03,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:07,989] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
44%|████▍ | 24/54 [33:12<40:13, 80.43s/it] {'loss': '0.2353', 'grad_norm': '0.3472', 'learning_rate': '7.996e-06', 'ppl': '1.265', 'memory/max_active (GiB)': '91.94', 'memory/max_allocated (GiB)': '91.94', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '79.15', 'tokens/total': 17848512, 'tokens/trainable': 6316892, 'epoch': '1.333'}
44%|████▍ | 24/54 [33:12<40:13, 80.43s/it][2026-04-23 05:29:08,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:08,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:09,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:10,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:10,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:10,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:10,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:10,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:10,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:18,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:19,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:20,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:20,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:20,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:30,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:31,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:32,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:39,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:40,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:41,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:48,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:49,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:50,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:29:59,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:00,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:01,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:01,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:08,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:09,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:10,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:20,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:21,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,530] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
46%|████▋ | 25/54 [34:33<39:02, 80.77s/it] {'loss': '0.2268', 'grad_norm': '0.323', 'learning_rate': '7.703e-06', 'ppl': '1.255', 'memory/max_active (GiB)': '90.17', 'memory/max_allocated (GiB)': '90.17', 'memory/device_reserved (GiB)': '92.5', 'tokens/train_per_sec_per_gpu': '97.78', 'tokens/total': 18632576, 'tokens/trainable': 6593565, 'epoch': '1.389'}
46%|████▋ | 25/54 [34:33<39:02, 80.77s/it][2026-04-23 05:30:29,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:29,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:30,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:31,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:38,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:38,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:38,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:39,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:40,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:50,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:51,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:57,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:58,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:30:59,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:04,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:05,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:06,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:15,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:16,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:25,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:25,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:25,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:25,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:25,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:26,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:27,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:36,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:36,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:36,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:36,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:36,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:37,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:38,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:45,962] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
48%|████▊ | 26/54 [35:50<37:05, 79.47s/it] {'loss': '0.2292', 'grad_norm': '0.3507', 'learning_rate': '7.396e-06', 'ppl': '1.258', 'memory/max_active (GiB)': '89.58', 'memory/max_allocated (GiB)': '89.58', 'memory/device_reserved (GiB)': '92.52', 'tokens/train_per_sec_per_gpu': '92.89', 'tokens/total': 19343104, 'tokens/trainable': 6843071, 'epoch': '1.444'}
48%|████▊ | 26/54 [35:50<37:05, 79.47s/it][2026-04-23 05:31:45,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:46,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:47,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:48,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:48,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:56,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:56,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:56,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:56,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:56,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:56,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:57,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:31:58,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:06,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:07,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:08,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:18,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:19,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:20,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:20,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:20,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:20,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:20,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:29,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:29,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:29,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:29,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:30,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:31,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:39,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:40,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:41,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:51,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:52,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:32:53,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:02,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:02,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:02,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:02,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:02,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:02,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:03,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:04,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,486] [WARNING] [stage3.py:2497:step] 10 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
50%|█████ | 27/54 [37:19<37:07, 82.48s/it] {'loss': '0.2317', 'grad_norm': '0.3314', 'learning_rate': '7.077e-06', 'ppl': '1.261', 'memory/max_active (GiB)': '92.07', 'memory/max_allocated (GiB)': '92.07', 'memory/device_reserved (GiB)': '92.85', 'tokens/train_per_sec_per_gpu': '94.89', 'tokens/total': 20132544, 'tokens/trainable': 7103225, 'epoch': '1.5'}
50%|█████ | 27/54 [37:19<37:07, 82.48s/it][2026-04-23 05:33:15,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:15,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:16,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:17,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:26,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:27,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:28,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:38,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:39,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:48,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:49,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:33:50,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:00,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:01,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:07,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:08,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:09,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:09,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:09,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:09,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:18,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:19,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:20,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:29,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:30,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:35,776] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
52%|█████▏ | 28/54 [38:40<35:27, 81.83s/it] {'loss': '0.2127', 'grad_norm': '0.297', 'learning_rate': '6.747e-06', 'ppl': '1.237', 'memory/max_active (GiB)': '88.54', 'memory/max_allocated (GiB)': '88.54', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '64.31', 'tokens/total': 20894528, 'tokens/trainable': 7367374, 'epoch': '1.556'}
52%|█████▏ | 28/54 [38:40<35:27, 81.83s/it][2026-04-23 05:34:35,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:35,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:35,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:35,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:35,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:36,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:37,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:46,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:47,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:48,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:48,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:48,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:48,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:57,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:58,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:59,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:59,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:59,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:59,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:34:59,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:07,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:08,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:09,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:09,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:09,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:09,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:09,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:19,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:20,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:27,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:27,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:27,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:28,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:29,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:37,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:37,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:37,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:37,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:37,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:38,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:39,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:40,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:40,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:40,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:40,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:49,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:50,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:51,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:51,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:51,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:51,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:51,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,003] [WARNING] [stage3.py:2497:step] 8 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
54%|█████▎ | 29/54 [40:02<34:08, 81.95s/it] {'loss': '0.207', 'grad_norm': '0.3122', 'learning_rate': '6.409e-06', 'ppl': '1.23', 'memory/max_active (GiB)': '91.82', 'memory/max_allocated (GiB)': '91.82', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '74.57', 'tokens/total': 21655104, 'tokens/trainable': 7636594, 'epoch': '1.611'}
54%|█████▎ | 29/54 [40:02<34:08, 81.95s/it][2026-04-23 05:35:58,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:58,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:35:59,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:00,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:00,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:08,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:09,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:10,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:10,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:10,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:10,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:10,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:18,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:19,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:20,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:20,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:20,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:20,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:20,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:26,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:27,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:35,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:36,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:37,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:37,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:37,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:37,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:37,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:37,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:45,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:46,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:47,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:56,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:57,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:36:58,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:04,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:05,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:06,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:16,728] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
56%|█████▌ | 30/54 [41:21<32:23, 80.98s/it] {'loss': '0.2083', 'grad_norm': '0.2769', 'learning_rate': '6.063e-06', 'ppl': '1.232', 'memory/max_active (GiB)': '89.35', 'memory/max_allocated (GiB)': '89.35', 'memory/device_reserved (GiB)': '92.51', 'tokens/train_per_sec_per_gpu': '123.4', 'tokens/total': 22403136, 'tokens/trainable': 7907965, 'epoch': '1.667'}
56%|█████▌ | 30/54 [41:21<32:23, 80.98s/it][2026-04-23 05:37:16,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:16,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:16,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:16,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:16,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:16,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:17,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:18,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:25,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:26,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:27,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:36,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:37,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:38,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:38,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:38,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:38,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:44,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:45,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:46,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:55,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:56,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:37:57,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:08,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:09,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:10,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:19,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:20,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:26,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:27,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:28,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:28,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:28,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,294] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
57%|█████▋ | 31/54 [42:41<30:59, 80.86s/it] {'loss': '0.213', 'grad_norm': '0.2979', 'learning_rate': '5.712e-06', 'ppl': '1.237', 'memory/max_active (GiB)': '91.71', 'memory/max_allocated (GiB)': '91.71', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '94.94', 'tokens/total': 23121920, 'tokens/trainable': 8161634, 'epoch': '1.722'}
57%|█████▋ | 31/54 [42:41<30:59, 80.86s/it][2026-04-23 05:38:37,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:37,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:38,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:39,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:39,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:39,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:39,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:39,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:39,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:47,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:48,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:49,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:49,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:49,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:49,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:49,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:49,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:58,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:38:59,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:00,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:00,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:00,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:00,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:08,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:09,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:10,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:19,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:20,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:21,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:21,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:21,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:21,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:29,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:30,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:31,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:40,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:41,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:42,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:50,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:51,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:39:52,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,233] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
59%|█████▉ | 32/54 [44:06<30:05, 82.08s/it] {'loss': '0.2019', 'grad_norm': '0.2818', 'learning_rate': '5.357e-06', 'ppl': '1.224', 'memory/max_active (GiB)': '91.12', 'memory/max_allocated (GiB)': '91.12', 'memory/device_reserved (GiB)': '92.85', 'tokens/train_per_sec_per_gpu': '77.07', 'tokens/total': 23855936, 'tokens/trainable': 8430566, 'epoch': '1.778'}
59%|█████▉ | 32/54 [44:06<30:05, 82.08s/it][2026-04-23 05:40:02,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:02,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:03,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:04,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:04,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:11,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:12,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:13,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:13,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:13,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:13,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:13,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:21,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:21,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:21,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:22,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:23,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:32,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:33,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:34,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:34,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:34,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:34,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:42,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:43,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:50,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:51,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:40:52,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:00,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:00,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:00,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:00,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:00,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:01,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:02,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:11,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:12,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:13,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,434] [WARNING] [stage3.py:2497:step] 4 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
61%|██████ | 33/54 [45:27<28:38, 81.82s/it] {'loss': '0.2026', 'grad_norm': '0.2789', 'learning_rate': '5e-06', 'ppl': '1.225', 'memory/max_active (GiB)': '82.86', 'memory/max_allocated (GiB)': '82.86', 'memory/device_reserved (GiB)': '92.85', 'tokens/train_per_sec_per_gpu': '121.6', 'tokens/total': 24612608, 'tokens/trainable': 8688733, 'epoch': '1.833'}
61%|██████ | 33/54 [45:27<28:38, 81.82s/it][2026-04-23 05:41:23,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:23,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:24,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:25,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:31,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:31,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:31,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:31,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:32,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:33,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:42,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:42,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:42,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:42,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:42,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:42,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:43,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:44,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:53,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:54,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:55,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:55,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:55,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:55,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:55,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:41:55,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:04,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:05,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:06,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:15,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:16,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:17,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:25,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:26,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:27,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:36,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:36,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:36,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:36,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:36,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:37,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:38,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:48,948] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
63%|██████▎ | 34/54 [46:53<27:38, 82.93s/it] {'loss': '0.222', 'grad_norm': '0.2995', 'learning_rate': '4.643e-06', 'ppl': '1.249', 'memory/max_active (GiB)': '89.82', 'memory/max_allocated (GiB)': '89.82', 'memory/device_reserved (GiB)': '92.73', 'tokens/train_per_sec_per_gpu': '92.76', 'tokens/total': 25360512, 'tokens/trainable': 8947827, 'epoch': '1.889'}
63%|██████▎ | 34/54 [46:53<27:38, 82.93s/it][2026-04-23 05:42:48,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:49,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:50,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:51,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:51,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:51,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:59,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:59,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:42:59,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:00,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:01,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:10,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:10,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:10,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:10,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:10,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:10,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:11,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:12,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:20,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:20,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:20,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:20,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:20,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:21,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:22,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:31,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:31,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:31,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:31,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:31,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:32,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:33,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:34,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:34,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:43,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:44,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:45,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:45,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:45,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:45,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:45,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:45,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:53,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:54,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:43:59,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:00,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,050] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
65%|██████▍ | 35/54 [48:11<25:48, 81.48s/it] {'loss': '0.2018', 'grad_norm': '0.2529', 'learning_rate': '4.288e-06', 'ppl': '1.224', 'memory/max_active (GiB)': '91', 'memory/max_allocated (GiB)': '91', 'memory/device_reserved (GiB)': '92.79', 'tokens/train_per_sec_per_gpu': '90.4', 'tokens/total': 26059968, 'tokens/trainable': 9207796, 'epoch': '1.944'}
65%|██████▍ | 35/54 [48:11<25:48, 81.48s/it][2026-04-23 05:44:07,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:07,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:08,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:09,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:09,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:09,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:09,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:09,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:17,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:17,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:18,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:19,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:25,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:26,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:27,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:27,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:27,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:27,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:27,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:36,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:37,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:44,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:44,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:44,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:44,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:44,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:45,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:46,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:46,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:46,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:46,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:46,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:46,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:52,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:53,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:58,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:44:59,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:00,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:10,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:11,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:12,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:12,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:12,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:12,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:12,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:21,109] [WARNING] [stage3.py:2497:step] 4 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
67%|██████▋ | 36/54 [49:25<23:46, 79.25s/it] {'loss': '0.2065', 'grad_norm': '0.2529', 'learning_rate': '3.937e-06', 'ppl': '1.229', 'memory/max_active (GiB)': '89.7', 'memory/max_allocated (GiB)': '89.7', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '113.4', 'tokens/total': 26794304, 'tokens/trainable': 9474481, 'epoch': '2'}
67%|██████▋ | 36/54 [49:25<23:46, 79.25s/it][2026-04-23 05:45:24,616] [INFO] [axolotl.core.trainers.base._save:741] [PID:2005626] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B/checkpoint-36
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.80s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.80s/it]
[2026-04-23 05:45:51,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:51,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:45:52,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:00,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:01,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:06,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:07,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:08,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:16,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:16,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:16,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:16,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:16,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:16,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:17,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:18,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:28,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:28,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:29,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:30,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:40,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:41,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:42,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:51,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:52,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:46:53,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:00,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:01,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:02,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:09,882] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
69%|██████▊ | 37/54 [51:14<24:57, 88.11s/it] {'loss': '0.2067', 'grad_norm': '0.2889', 'learning_rate': '3.591e-06', 'ppl': '1.23', 'memory/max_active (GiB)': '91.59', 'memory/max_allocated (GiB)': '91.59', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '112', 'tokens/total': 27502976, 'tokens/trainable': 9718405, 'epoch': '2.056'}
69%|██████▊ | 37/54 [51:14<24:57, 88.11s/it][2026-04-23 05:47:09,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:09,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:10,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:11,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:12,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:12,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:20,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:21,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:22,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:22,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:22,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:22,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:22,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:22,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:31,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:32,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:33,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:33,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:41,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:41,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:41,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:41,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:41,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:41,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:42,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:43,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:52,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:52,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:52,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:52,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:52,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:52,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:53,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:47:54,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:00,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:01,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:02,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:11,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:12,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:13,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:21,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:22,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:23,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:23,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:23,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:23,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,274] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
70%|███████ | 38/54 [52:36<23:02, 86.39s/it] {'loss': '0.1926', 'grad_norm': '0.2694', 'learning_rate': '3.253e-06', 'ppl': '1.212', 'memory/max_active (GiB)': '88.75', 'memory/max_allocated (GiB)': '88.75', 'memory/device_reserved (GiB)': '92.79', 'tokens/train_per_sec_per_gpu': '86.9', 'tokens/total': 28273536, 'tokens/trainable': 9985626, 'epoch': '2.111'}
70%|███████ | 38/54 [52:36<23:02, 86.39s/it][2026-04-23 05:48:32,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:32,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:33,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:39,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:40,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:41,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:50,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:51,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:48:59,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:00,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:01,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:08,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:08,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:08,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:09,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:10,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:18,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:19,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:20,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:28,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:29,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:30,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:39,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:40,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:41,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,654] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
72%|███████▏ | 39/54 [53:54<20:55, 83.69s/it] {'loss': '0.1951', 'grad_norm': '0.2696', 'learning_rate': '2.923e-06', 'ppl': '1.215', 'memory/max_active (GiB)': '88.05', 'memory/max_allocated (GiB)': '88.05', 'memory/device_reserved (GiB)': '90.95', 'tokens/train_per_sec_per_gpu': '126.5', 'tokens/total': 28979072, 'tokens/trainable': 10237194, 'epoch': '2.167'}
72%|███████▏ | 39/54 [53:54<20:55, 83.69s/it][2026-04-23 05:49:49,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:49,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:50,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:51,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:58,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:49:59,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:00,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:00,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:00,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:00,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:00,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:00,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:08,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:09,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:10,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:20,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:21,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:22,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:29,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:29,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:29,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:29,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:29,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:30,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:31,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:40,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:41,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:50,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:50:51,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:00,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:01,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:02,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:09,810] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
74%|███████▍ | 40/54 [55:14<19:16, 82.63s/it] {'loss': '0.193', 'grad_norm': '0.2538', 'learning_rate': '2.604e-06', 'ppl': '1.213', 'memory/max_active (GiB)': '91.94', 'memory/max_allocated (GiB)': '91.94', 'memory/device_reserved (GiB)': '92.84', 'tokens/train_per_sec_per_gpu': '103.5', 'tokens/total': 29752576, 'tokens/trainable': 10511042, 'epoch': '2.222'}
74%|███████▍ | 40/54 [55:14<19:16, 82.63s/it][2026-04-23 05:51:09,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:09,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:09,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:09,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:10,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:11,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:12,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:12,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:12,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:12,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:12,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:20,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:20,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:20,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:20,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:20,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:21,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:22,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:30,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:30,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:31,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:32,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:33,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:33,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:33,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:41,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:41,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:41,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:41,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:41,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:41,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:42,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:43,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:53,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:54,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:51:55,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:03,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:04,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:14,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:15,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:25,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:26,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:27,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:27,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,233] [WARNING] [stage3.py:2497:step] 8 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
76%|███████▌ | 41/54 [56:40<18:08, 83.77s/it] {'loss': '0.1949', 'grad_norm': '0.3281', 'learning_rate': '2.297e-06', 'ppl': '1.215', 'memory/max_active (GiB)': '90.75', 'memory/max_allocated (GiB)': '90.75', 'memory/device_reserved (GiB)': '92.65', 'tokens/train_per_sec_per_gpu': '95.74', 'tokens/total': 30460032, 'tokens/trainable': 10762180, 'epoch': '2.278'}
76%|███████▌ | 41/54 [56:40<18:08, 83.77s/it][2026-04-23 05:52:36,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:36,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:37,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:38,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:48,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:49,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:50,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:51,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:52:51,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:00,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:00,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:01,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:02,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:09,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:10,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:11,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:11,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:11,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:11,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:19,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:20,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:21,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:21,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:29,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:30,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:37,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:38,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:39,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:46,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:47,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:48,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:48,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:48,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:48,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:48,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:58,791] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
78%|███████▊ | 42/54 [58:03<16:40, 83.40s/it] {'loss': '0.1834', 'grad_norm': '0.2538', 'learning_rate': '2.004e-06', 'ppl': '1.201', 'memory/max_active (GiB)': '82.86', 'memory/max_allocated (GiB)': '82.86', 'memory/device_reserved (GiB)': '92.34', 'tokens/train_per_sec_per_gpu': '128.1', 'tokens/total': 31249920, 'tokens/trainable': 11055754, 'epoch': '2.333'}
78%|███████▊ | 42/54 [58:03<16:40, 83.40s/it][2026-04-23 05:53:58,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:58,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:58,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:58,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:53:59,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:00,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:01,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:01,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:01,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:01,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:11,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:12,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:13,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:13,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:13,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:23,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:24,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:25,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:33,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:34,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:35,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:44,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:45,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:46,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:46,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:46,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:46,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:53,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:54,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:55,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:54:55,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:02,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:02,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:02,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:02,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:03,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:04,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:13,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:14,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:15,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:24,797] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
80%|███████▉ | 43/54 [59:29<15:26, 84.18s/it] {'loss': '0.1942', 'grad_norm': '0.2663', 'learning_rate': '1.726e-06', 'ppl': '1.214', 'memory/max_active (GiB)': '91', 'memory/max_allocated (GiB)': '91', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '48.05', 'tokens/total': 31983424, 'tokens/trainable': 11308688, 'epoch': '2.389'}
80%|███████▉ | 43/54 [59:29<15:26, 84.18s/it][2026-04-23 05:55:24,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:24,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:24,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:24,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:25,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:26,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:36,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:37,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:38,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:38,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:38,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:38,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:38,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:38,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:48,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:49,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:50,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:55:59,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:00,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:01,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:01,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:01,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:10,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:11,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:12,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:12,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:19,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:20,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:21,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:30,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:31,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:32,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:32,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:40,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:41,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:42,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:48,736] [WARNING] [stage3.py:2497:step] 2 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
81%|████████▏ | 44/54 [1:00:53<14:01, 84.11s/it] {'loss': '0.1644', 'grad_norm': '0.2389', 'learning_rate': '1.464e-06', 'ppl': '1.179', 'memory/max_active (GiB)': '86.65', 'memory/max_allocated (GiB)': '86.65', 'memory/device_reserved (GiB)': '90.84', 'tokens/train_per_sec_per_gpu': '96.7', 'tokens/total': 32773504, 'tokens/trainable': 11600519, 'epoch': '2.444'}
81%|████████▏ | 44/54 [1:00:53<14:01, 84.11s/it][2026-04-23 05:56:48,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:48,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:48,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:48,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:48,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:49,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:50,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:58,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:58,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:58,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:58,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:56:59,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:00,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:09,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:10,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:11,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:11,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:11,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:20,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:21,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:22,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:30,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:31,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:32,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:42,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:43,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:51,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:51,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:51,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:51,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:51,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:52,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:57:53,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:02,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:03,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,240] [WARNING] [stage3.py:2497:step] 8 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
83%|████████▎ | 45/54 [1:02:15<12:32, 83.63s/it] {'loss': '0.1881', 'grad_norm': '0.2566', 'learning_rate': '1.221e-06', 'ppl': '1.207', 'memory/max_active (GiB)': '88.52', 'memory/max_allocated (GiB)': '88.52', 'memory/device_reserved (GiB)': '91.6', 'tokens/train_per_sec_per_gpu': '67.89', 'tokens/total': 33513664, 'tokens/trainable': 11869906, 'epoch': '2.5'}
83%|████████▎ | 45/54 [1:02:15<12:32, 83.63s/it][2026-04-23 05:58:11,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:11,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:12,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:19,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:20,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:21,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:21,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:21,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:29,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:30,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:31,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:31,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:31,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:39,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:40,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:48,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:49,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:58:50,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:00,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:01,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:07,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:07,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:07,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:07,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:07,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:07,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:08,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:09,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:18,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:19,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:20,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:20,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:20,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:27,855] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
85%|████████▌ | 46/54 [1:03:32<10:52, 81.52s/it] {'loss': '0.1801', 'grad_norm': '0.5517', 'learning_rate': '9.973e-07', 'ppl': '1.197', 'memory/max_active (GiB)': '90.53', 'memory/max_allocated (GiB)': '90.53', 'memory/device_reserved (GiB)': '92.4', 'tokens/train_per_sec_per_gpu': '101.9', 'tokens/total': 34197632, 'tokens/trainable': 12087498, 'epoch': '2.556'}
85%|████████▌ | 46/54 [1:03:32<10:52, 81.52s/it][2026-04-23 05:59:27,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:27,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:27,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:28,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:29,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:38,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:39,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:40,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:49,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:50,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:51,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:51,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:57,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 05:59:58,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:07,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:08,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:09,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:09,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:09,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:09,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:16,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:17,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:18,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:24,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:25,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:26,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:26,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:26,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:26,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:34,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:35,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,203] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
87%|████████▋ | 47/54 [1:04:46<09:15, 79.37s/it] {'loss': '0.1809', 'grad_norm': '0.2502', 'learning_rate': '7.937e-07', 'ppl': '1.198', 'memory/max_active (GiB)': '86.4', 'memory/max_allocated (GiB)': '86.4', 'memory/device_reserved (GiB)': '92.55', 'tokens/train_per_sec_per_gpu': '93.97', 'tokens/total': 34903488, 'tokens/trainable': 12342673, 'epoch': '2.611'}
87%|████████▋ | 47/54 [1:04:46<09:15, 79.37s/it][2026-04-23 06:00:42,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:42,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:43,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:44,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:44,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:44,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:44,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:44,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:44,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:52,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:53,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:00:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:02,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:03,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:04,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:04,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:04,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:04,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:13,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:14,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:15,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:15,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:15,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:21,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:21,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:21,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:21,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:22,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:23,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:24,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:24,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:33,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:34,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:35,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:35,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:43,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:44,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:45,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:54,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:55,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:56,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:56,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:56,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:56,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:01:56,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,592] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
89%|████████▉ | 48/54 [1:06:07<07:59, 79.98s/it] {'loss': '0.2017', 'grad_norm': '0.3003', 'learning_rate': '6.116e-07', 'ppl': '1.223', 'memory/max_active (GiB)': '92.06', 'memory/max_allocated (GiB)': '92.06', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '102.6', 'tokens/total': 35639808, 'tokens/trainable': 12605608, 'epoch': '2.667'}
89%|████████▉ | 48/54 [1:06:07<07:59, 79.98s/it][2026-04-23 06:02:03,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:03,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:04,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:05,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:14,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:15,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:16,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:16,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:16,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:16,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:16,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:26,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:27,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:32,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:32,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:33,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:34,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:41,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:42,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:43,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:53,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:54,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:02:55,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:03,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:04,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:05,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:14,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:15,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:16,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:16,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,318] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
91%|█████████ | 49/54 [1:07:29<06:42, 80.50s/it] {'loss': '0.1907', 'grad_norm': '0.2599', 'learning_rate': '4.518e-07', 'ppl': '1.21', 'memory/max_active (GiB)': '86.28', 'memory/max_allocated (GiB)': '86.28', 'memory/device_reserved (GiB)': '92.49', 'tokens/train_per_sec_per_gpu': '101.5', 'tokens/total': 36429696, 'tokens/trainable': 12876573, 'epoch': '2.722'}
91%|█████████ | 49/54 [1:07:29<06:42, 80.50s/it][2026-04-23 06:03:25,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:25,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:26,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:27,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:27,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:27,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:27,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:27,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:35,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:36,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:41,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:42,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:43,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:43,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:43,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:43,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:43,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:51,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:51,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:51,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:51,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:52,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:03:53,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:03,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:04,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:05,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:14,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:15,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:16,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:24,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:25,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:26,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:35,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:35,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:35,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:36,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:37,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,373] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
93%|█████████▎| 50/54 [1:08:47<05:19, 79.77s/it] {'loss': '0.1726', 'grad_norm': '0.2403', 'learning_rate': '3.153e-07', 'ppl': '1.188', 'memory/max_active (GiB)': '90.41', 'memory/max_allocated (GiB)': '90.41', 'memory/device_reserved (GiB)': '92.3', 'tokens/train_per_sec_per_gpu': '92.51', 'tokens/total': 37139712, 'tokens/trainable': 13134242, 'epoch': '2.778'}
93%|█████████▎| 50/54 [1:08:47<05:19, 79.77s/it][2026-04-23 06:04:43,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:43,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:44,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:45,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:53,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:53,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:53,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:53,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:53,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:54,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:04:55,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:03,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:03,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:03,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:03,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:04,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:05,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:15,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:16,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:17,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:17,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:17,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:17,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:17,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:17,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:25,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:25,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:25,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:25,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:26,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:27,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:28,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:37,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:37,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:37,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:38,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:39,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:48,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:48,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:48,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:49,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:50,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:58,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:05:59,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:00,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,073] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
94%|█████████▍| 51/54 [1:10:14<04:05, 81.85s/it] {'loss': '0.1771', 'grad_norm': '0.2324', 'learning_rate': '2.025e-07', 'ppl': '1.194', 'memory/max_active (GiB)': '91.82', 'memory/max_allocated (GiB)': '91.82', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '95.33', 'tokens/total': 37937024, 'tokens/trainable': 13419951, 'epoch': '2.833'}
94%|█████████▍| 51/54 [1:10:14<04:05, 81.85s/it][2026-04-23 06:06:10,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:10,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:11,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:17,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:18,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:26,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:27,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:28,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:37,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:37,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:37,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:38,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:39,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:48,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:48,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:48,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:48,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:48,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:49,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:06:50,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:01,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:02,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:10,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:11,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:18,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:19,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:20,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,089] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
96%|█████████▋| 52/54 [1:11:35<02:43, 81.60s/it] {'loss': '0.1935', 'grad_norm': '0.2507', 'learning_rate': '1.143e-07', 'ppl': '1.214', 'memory/max_active (GiB)': '90.64', 'memory/max_allocated (GiB)': '90.64', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '134', 'tokens/total': 38694848, 'tokens/trainable': 13686769, 'epoch': '2.889'}
96%|█████████▋| 52/54 [1:11:35<02:43, 81.60s/it][2026-04-23 06:07:31,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:31,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:32,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:33,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:33,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:33,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:41,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:42,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:50,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:51,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:58,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:07:59,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:00,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:00,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:00,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:00,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:07,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:08,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:09,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:18,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:19,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:20,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:20,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:20,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:20,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:28,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:28,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:28,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:28,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:29,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:30,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:38,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:39,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:40,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:49,708] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
98%|█████████▊| 53/54 [1:12:54<01:20, 80.70s/it] {'loss': '0.1862', 'grad_norm': '0.2569', 'learning_rate': '5.089e-08', 'ppl': '1.205', 'memory/max_active (GiB)': '87.22', 'memory/max_allocated (GiB)': '87.22', 'memory/device_reserved (GiB)': '92.83', 'tokens/train_per_sec_per_gpu': '103.2', 'tokens/total': 39421760, 'tokens/trainable': 13950364, 'epoch': '2.944'}
98%|█████████▊| 53/54 [1:12:54<01:20, 80.70s/it][2026-04-23 06:08:49,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:49,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:49,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:49,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:49,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:50,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:08:51,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:01,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:02,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:08,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:09,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:10,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:10,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:10,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:10,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:10,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:20,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:21,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:22,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:22,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:29,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:30,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:31,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:42,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:43,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:44,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:44,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:44,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:44,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:44,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:51,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:52,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:09:53,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:02,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:03,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 06:10:09,235] [WARNING] [stage3.py:2497:step] 10 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
100%|██████████| 54/54 [1:14:13<00:00, 80.35s/it] {'loss': '0.1931', 'grad_norm': '0.267', 'learning_rate': '1.274e-08', 'ppl': '1.213', 'memory/max_active (GiB)': '91.59', 'memory/max_allocated (GiB)': '91.59', 'memory/device_reserved (GiB)': '92.85', 'tokens/train_per_sec_per_gpu': '76.65', 'tokens/total': 40187456, 'tokens/trainable': 14209761, 'epoch': '3'}
100%|██████████| 54/54 [1:14:13<00:00, 80.35s/it][2026-04-23 06:10:11,371] [INFO] [axolotl.core.trainers.base._save:741] [PID:2005626] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B/checkpoint-54
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.07s/it] Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.07s/it]
{'train_runtime': '4475', 'train_samples_per_second': '0.386', 'train_steps_per_second': '0.012', 'train_loss': '0.2739', 'memory/max_active (GiB)': '31.77', 'memory/max_allocated (GiB)': '31.77', 'memory/device_reserved (GiB)': '85.82', 'epoch': '3', 'tokens/train_per_sec_per_gpu': '0'}
100%|██████████| 54/54 [1:14:34<00:00, 80.35s/it] 100%|██████████| 54/54 [1:14:34<00:00, 82.87s/it]
[2026-04-23 06:10:31,416] [INFO] [axolotl.train.save_trained_model:241] [PID:2005626] Training completed! Saving trained model to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B.
[2026-04-23 06:10:33,516] [INFO] [axolotl.core.trainers.base._save:741] [PID:2005626] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s] Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.00s/it] Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.00s/it]
[2026-04-23 06:10:40,713] [INFO] [axolotl.train.save_trained_model:355] [PID:2005626] Model successfully saved to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B