Files

9812 lines
1.5 MiB
Plaintext
Raw Permalink Normal View History

[2026-04-24 14:28:26,498] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:1476492] bf16 support detected, enabling for this configuration.
[2026-04-24 14:28:26,510] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:1476492] baseline 0.000GB ()
[2026-04-24 14:28:26,510] [INFO] [axolotl.cli.config.load_cfg:341] [PID:1476492] 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_316_v3.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": "tokenizer_default",
"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-v4-316-v3",
"datasets": [
{
"chat_template": "tokenizer_default",
"ds_type": "json",
"field_messages": "messages",
"message_field_training": "train",
"message_property_mappings": {
"content": "content",
"role": "role"
},
"path": "/e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--Sera-4.6-Lite-T2-v4-316/snapshots/2df0e5321c676c5010ba43d4be6b74fb13dfe8a4/sera-4.6-lite-t2_v4_316.jsonl",
"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": 6.0,
"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-v4-316-axolotl__Qwen3-8B-v3",
"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-v4-316-axolotl__Qwen3-8B-v3",
"warmup_ratio": 0.1875,
"weight_decay": 0.01,
"world_size": 4
}
[2026-04-24 14:28:26,527] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:1476492] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.
[2026-04-24 14:28:27,001] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:1476492] EOS: 151645 / <|im_end|>
[2026-04-24 14:28:27,001] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:1476492] BOS: None / None
[2026-04-24 14:28:27,001] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:1476492] PAD: 151643 / <|endoftext|>
[2026-04-24 14:28:27,001] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:1476492] UNK: None / None
[2026-04-24 14:28:27,056] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:1476492] Loading prepared dataset from disk at /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-316-v3/6a9b456bfb3853b790bb0bd3a8fbe97e...
[2026-04-24 14:28:27,065] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:1476492] total_num_tokens: 4_184_767
[2026-04-24 14:28:27,132] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:1476492] `total_supervised_tokens: 1_482_765`
[2026-04-24 14:28:27,132] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:1476492] total_num_steps: 34
[2026-04-24 14:28:27,132] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:1476492] Maximum number of steps set at 34
[2026-04-24 14:28:27,169] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:1476492] loading tokenizer... Qwen/Qwen3-8B
[2026-04-24 14:28:27,429] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:1476492] EOS: 151645 / <|im_end|>
[2026-04-24 14:28:27,430] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:1476492] BOS: None / None
[2026-04-24 14:28:27,430] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:1476492] PAD: 151643 / <|endoftext|>
[2026-04-24 14:28:27,430] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:1476492] UNK: None / None
[2026-04-24 14:28:27,430] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:1476492] Loading model
[2026-04-24 14:28:27,436] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:1476492] Patched Trainer.evaluation_loop with nanmean loss calculation
[2026-04-24 14:28:27,437] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:1476492] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
[2026-04-24 14:28:27,506] [INFO] [axolotl.monkeypatch.attention.flash_attn_4.patch_flash_attn_4:52] [PID:1476492] Flash Attention 4 is available for your GPU and offers faster training speeds. To enable: pip install flash-attn-4
[2026-04-24 14:28:27,507] [INFO] [axolotl.monkeypatch.deepspeed_utils.patch_checkpoint_wrapper_setattr:52] [PID:1476492] CheckpointWrapper patched to forward DeepSpeed attributes
[2026-04-24 14:28:38,153] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:1476492] Converting modules to torch.bfloat16
[2026-04-24 14:28:38,157] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:1476492] Memory usage after model load 4.973GB (+4.973GB allocated, +5.080GB reserved)
[2026-04-24 14:28:41,359] [INFO] [axolotl.train.save_initial_configs:421] [PID:1476492] Pre-saving tokenizer to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3...
[2026-04-24 14:28:41,468] [INFO] [axolotl.train.save_initial_configs:426] [PID:1476492] Pre-saving model config to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3...
[2026-04-24 14:28:41,473] [INFO] [axolotl.train.execute_training:222] [PID:1476492] Starting trainer...
[2026-04-24 14:28:41,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:41,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_id to wrapped module Qwen3DecoderLayer
0%| | 0/34 [00:00<?, ?it/s][2026-04-24 14:28:43,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:44,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:45,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:54,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:55,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:28:56,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:07,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:07,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:07,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:07,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:07,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:07,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:08,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:09,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:16,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:17,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:18,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:18,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:18,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:26,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:26,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:27,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:28,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:36,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:37,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:38,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:50,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:51,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:52,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:29:59,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:00,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:01,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:01,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:01,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:01,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:01,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
3%|▎ | 1/34 [01:24<46:36, 84.75s/it] {'loss': '0.523', 'grad_norm': '12.89', 'learning_rate': '0', 'ppl': '1.687', 'memory/max_active (GiB)': '75.39', 'memory/max_allocated (GiB)': '75.39', 'memory/device_reserved (GiB)': '89.04', 'tokens/train_per_sec_per_gpu': '69.37', 'tokens/total': 756928, 'tokens/trainable': 273715, 'epoch': '0.1739'}
3%|▎ | 1/34 [01:24<46:36, 84.75s/it][2026-04-24 14:30:07,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:07,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:07,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:07,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:07,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:07,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:07,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:08,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:09,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:16,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:17,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:18,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:28,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:29,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:30,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:30,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:30,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:38,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:39,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:47,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:47,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:47,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:47,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:47,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:48,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:49,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:56,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:57,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:58,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:58,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:30:58,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:04,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:05,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:06,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:06,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:06,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:06,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:14,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:15,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:24,998] [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
6%|▌ | 2/34 [02:42<42:52, 80.39s/it] {'loss': '0.5105', 'grad_norm': '12.64', 'learning_rate': '1.667e-06', 'ppl': '1.666', 'memory/max_active (GiB)': '86.04', 'memory/max_allocated (GiB)': '86.04', 'memory/device_reserved (GiB)': '92.47', 'tokens/train_per_sec_per_gpu': '91.58', 'tokens/total': 1493248, 'tokens/trainable': 530455, 'epoch': '0.3478'}
6%|▌ | 2/34 [02:42<42:52, 80.39s/it][2026-04-24 14:31:25,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:25,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:26,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:27,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:28,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:28,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:28,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:28,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:37,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:38,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:43,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:44,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:45,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:54,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:31:55,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:00,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:01,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:02,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:02,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:02,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:02,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:02,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:02,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:10,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:11,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:12,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:12,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:12,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:12,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:20,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:21,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:29,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:29,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:29,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:29,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:29,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:29,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:30,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:31,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,104] [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
9%|▉ | 3/34 [03:57<40:17, 77.97s/it] {'loss': '0.5286', 'grad_norm': '13.56', 'learning_rate': '3.333e-06', 'ppl': '1.697', 'memory/max_active (GiB)': '89.23', 'memory/max_allocated (GiB)': '89.23', 'memory/device_reserved (GiB)': '92.77', 'tokens/train_per_sec_per_gpu': '120.2', 'tokens/total': 2202624, 'tokens/trainable': 763199, 'epoch': '0.5217'}
9%|▉ | 3/34 [03:57<40:17, 77.97s/it][2026-04-24 14:32:40,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:40,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:41,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:48,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:49,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:50,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:50,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:50,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:50,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:50,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:50,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:58,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:32:59,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:06,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:07,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:08,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:17,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:18,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:19,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:19,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:19,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:25,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:26,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:27,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:33,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:34,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:35,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:45,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:46,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:47,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:47,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:55,943] [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
12%|█▏ | 4/34 [05:13<38:33, 77.13s/it] {'loss': '0.4396', 'grad_norm': '6.06', 'learning_rate': '5e-06', 'ppl': '1.552', 'memory/max_active (GiB)': '86.75', 'memory/max_allocated (GiB)': '86.75', 'memory/device_reserved (GiB)': '92.83', 'tokens/train_per_sec_per_gpu': '110.4', 'tokens/total': 2915648, 'tokens/trainable': 1027748, 'epoch': '0.6957'}
12%|█▏ | 4/34 [05:13<38:33, 77.13s/it][2026-04-24 14:33:55,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:55,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:56,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:33:57,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:03,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:03,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:03,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:03,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:04,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:05,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:06,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:14,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:15,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:16,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:16,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:16,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:16,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:16,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:22,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:23,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:24,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:24,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:24,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:24,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:33,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:34,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:35,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:44,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:45,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:46,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:46,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:46,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:46,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:46,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:53,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:54,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:55,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:55,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:34:55,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:04,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:05,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:06,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:14,854] [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
15%|█▍ | 5/34 [06:31<37:35, 77.77s/it] {'loss': '0.4023', 'grad_norm': '2.164', 'learning_rate': '6.667e-06', 'ppl': '1.495', 'memory/max_active (GiB)': '86.63', 'memory/max_allocated (GiB)': '86.63', 'memory/device_reserved (GiB)': '92.51', 'tokens/train_per_sec_per_gpu': '108.6', 'tokens/total': 3641600, 'tokens/trainable': 1275566, 'epoch': '0.8696'}
15%|█▍ | 5/34 [06:31<37:35, 77.77s/it][2026-04-24 14:35:14,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:14,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:14,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:15,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:16,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:17,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:17,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:27,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:28,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:29,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:29,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:29,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:29,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:36,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:37,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:38,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:48,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:49,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:35:50,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:00,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:01,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:02,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:02,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:02,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:02,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:09,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:09,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:09,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:10,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:11,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:12,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:12,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:12,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:21,969] [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
18%|█▊ | 6/34 [07:39<34:36, 74.15s/it] {'loss': '0.3546', 'grad_norm': '1.388', 'learning_rate': '8.333e-06', 'ppl': '1.426', 'memory/max_active (GiB)': '92.19', 'memory/max_allocated (GiB)': '92.19', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '139.1', 'tokens/total': 4269440, 'tokens/trainable': 1510968, 'epoch': '1'}
18%|█▊ | 6/34 [07:39<34:36, 74.15s/it][2026-04-24 14:36:24,187] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3/checkpoint-6
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.93s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.93s/it]
[2026-04-24 14:36:54,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:54,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:54,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:54,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:54,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:54,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:55,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:36:56,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:05,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:06,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:15,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:16,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:17,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:25,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:26,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:27,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:35,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:36,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:37,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:45,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:46,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:47,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:57,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:37:58,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:06,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:07,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:08,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:08,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:08,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:15,880] [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
21%|██ | 7/34 [09:32<39:13, 87.15s/it] {'loss': '0.3506', 'grad_norm': '1.221', 'learning_rate': '1e-05', 'ppl': '1.42', 'memory/max_active (GiB)': '92.06', 'memory/max_allocated (GiB)': '92.06', 'memory/device_reserved (GiB)': '92.8', 'tokens/train_per_sec_per_gpu': '92.36', 'tokens/total': 4995136, 'tokens/trainable': 1769921, 'epoch': '1.174'}
21%|██ | 7/34 [09:32<39:13, 87.15s/it][2026-04-24 14:38:15,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:15,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:15,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:16,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:17,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:24,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:25,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:26,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:34,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:35,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:42,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:43,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:44,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:51,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:51,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:51,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:52,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:38:53,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:00,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:01,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:02,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:13,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:14,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:23,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:24,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,204] [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
24%|██▎ | 8/34 [10:49<36:16, 83.70s/it] {'loss': '0.3492', 'grad_norm': '0.8753', 'learning_rate': '9.969e-06', 'ppl': '1.418', 'memory/max_active (GiB)': '81.44', 'memory/max_allocated (GiB)': '81.44', 'memory/device_reserved (GiB)': '91.99', 'tokens/train_per_sec_per_gpu': '99.42', 'tokens/total': 5731968, 'tokens/trainable': 2028586, 'epoch': '1.348'}
24%|██▎ | 8/34 [10:49<36:16, 83.70s/it][2026-04-24 14:39:32,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:32,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:33,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:39,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:39,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:39,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:39,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:39,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:39,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:40,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:41,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:48,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:49,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:50,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:50,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:50,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:50,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:50,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:50,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:39:59,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:00,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:01,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:10,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:11,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:12,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:12,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:12,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:12,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:12,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:21,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:22,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:23,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:30,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:30,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:31,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:32,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:42,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:43,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:44,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,654] [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
26%|██▋ | 9/34 [12:08<34:19, 82.37s/it] {'loss': '0.3157', 'grad_norm': '0.801', 'learning_rate': '9.875e-06', 'ppl': '1.371', 'memory/max_active (GiB)': '80.02', 'memory/max_allocated (GiB)': '80.02', 'memory/device_reserved (GiB)': '90.87', 'tokens/train_per_sec_per_gpu': '111.8', 'tokens/total': 6459712, 'tokens/trainable': 2280990, 'epoch': '1.522'}
26%|██▋ | 9/34 [12:08<34:19, 82.37s/it][2026-04-24 14:40:51,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:51,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:52,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:40:53,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:00,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:01,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:02,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:11,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:12,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:13,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:22,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:23,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:29,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:29,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:29,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:30,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:31,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:40,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:41,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:42,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:52,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:53,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:54,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:54,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:41:54,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:01,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:02,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,153] [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
29%|██▉ | 10/34 [13:28<32:35, 81.49s/it] {'loss': '0.2814', 'grad_norm': '0.7557', 'learning_rate': '9.719e-06', 'ppl': '1.325', 'memory/max_active (GiB)': '85.57', 'memory/max_allocated (GiB)': '85.57', 'memory/device_reserved (GiB)': '92.1', 'tokens/train_per_sec_per_gpu': '112.1', 'tokens/total': 7194304, 'tokens/trainable': 2538254, 'epoch': '1.696'}
29%|██▉ | 10/34 [13:28<32:35, 81.49s/it][2026-04-24 14:42:11,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:11,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:12,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:18,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:19,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:20,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:30,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:31,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:32,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:43,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:44,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:45,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:52,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:53,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:42:54,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:04,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:05,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:06,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:06,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:06,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:06,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:06,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:06,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:14,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:14,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:15,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:16,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:26,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:27,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:28,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:28,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,329] [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
32%|███▏ | 11/34 [14:52<31:33, 82.31s/it] {'loss': '0.2592', 'grad_norm': '0.4596', 'learning_rate': '9.505e-06', 'ppl': '1.296', 'memory/max_active (GiB)': '90.41', 'memory/max_allocated (GiB)': '90.41', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '100.5', 'tokens/total': 7965760, 'tokens/trainable': 2811597, 'epoch': '1.87'}
32%|███▏ | 11/34 [14:52<31:33, 82.31s/it][2026-04-24 14:43:35,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:35,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:36,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:37,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:37,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:37,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:37,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:44,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:45,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:46,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:46,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:46,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:54,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:55,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:56,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:56,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:56,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:56,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:43:56,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:04,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:04,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:04,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:04,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:04,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:05,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:06,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:15,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:15,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:16,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:17,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:18,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:18,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:27,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:28,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:29,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:44:39,492] [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%|███▌ | 12/34 [15:56<28:09, 76.79s/it] {'loss': '0.2734', 'grad_norm': '0.5285', 'learning_rate': '9.234e-06', 'ppl': '1.314', 'memory/max_active (GiB)': '91.71', 'memory/max_allocated (GiB)': '91.71', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '156.8', 'tokens/total': 8529408, 'tokens/trainable': 3021524, 'epoch': '2'}
35%|███▌ | 12/34 [15:56<28:09, 76.79s/it][2026-04-24 14:44:41,749] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3/checkpoint-12
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]
[2026-04-24 14:45:10,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:10,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:11,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:12,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:12,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:12,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:20,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:20,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:20,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:20,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:21,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:22,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:31,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:32,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:33,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:42,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:43,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:44,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:44,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:44,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:44,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:51,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:52,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:45:53,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:00,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:01,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:07,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:08,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:09,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:09,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:09,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:09,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:09,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:09,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:18,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:18,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:18,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:18,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:18,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:19,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:20,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:21,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:21,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:30,968] [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
38%|███▊ | 13/34 [17:48<30:33, 87.30s/it] {'loss': '0.2525', 'grad_norm': '0.5079', 'learning_rate': '8.909e-06', 'ppl': '1.287', 'memory/max_active (GiB)': '89.23', 'memory/max_allocated (GiB)': '89.23', 'memory/device_reserved (GiB)': '92.81', 'tokens/train_per_sec_per_gpu': '101.8', 'tokens/total': 9268672, 'tokens/trainable': 3279227, 'epoch': '2.174'}
38%|███▊ | 13/34 [17:48<30:33, 87.30s/it][2026-04-24 14:46:31,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:31,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:32,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:41,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:42,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:43,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:51,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:51,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:51,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:51,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:52,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:53,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:46:59,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:00,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:06,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:07,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:14,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:15,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:25,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:26,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:27,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:27,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:27,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:27,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:27,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:35,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:35,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:35,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:35,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:35,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:35,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:36,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:37,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:46,759] [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%|████ | 14/34 [19:03<27:56, 83.82s/it] {'loss': '0.2524', 'grad_norm': '0.4531', 'learning_rate': '8.536e-06', 'ppl': '1.287', 'memory/max_active (GiB)': '89.94', 'memory/max_allocated (GiB)': '89.94', 'memory/device_reserved (GiB)': '91.73', 'tokens/train_per_sec_per_gpu': '102.9', 'tokens/total': 9985536, 'tokens/trainable': 3527848, 'epoch': '2.348'}
41%|████ | 14/34 [19:03<27:56, 83.82s/it][2026-04-24 14:47:46,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:46,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:46,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:46,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:46,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:46,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:47,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:48,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:53,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:54,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:47:55,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:03,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:03,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:03,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:03,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:03,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:03,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:04,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:05,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:15,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:16,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:17,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:17,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:17,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:17,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:17,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:17,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:26,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:27,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:36,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:37,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:38,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:38,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:38,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:38,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:38,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:38,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:46,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:46,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:46,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:46,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:46,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:47,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:48,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:49,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:58,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:48:59,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:00,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,091] [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
44%|████▍ | 15/34 [20:25<26:18, 83.07s/it] {'loss': '0.2349', 'grad_norm': '0.4078', 'learning_rate': '8.117e-06', 'ppl': '1.265', 'memory/max_active (GiB)': '91.71', 'memory/max_allocated (GiB)': '91.71', 'memory/device_reserved (GiB)': '92.82', 'tokens/train_per_sec_per_gpu': '105.7', 'tokens/total': 10687808, 'tokens/trainable': 3783560, 'epoch': '2.522'}
44%|████▍ | 15/34 [20:25<26:18, 83.07s/it][2026-04-24 14:49:08,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:08,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:09,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:15,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:16,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:17,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:24,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:25,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:26,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:35,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:35,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:35,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:36,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:37,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:44,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:45,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:46,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:56,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:56,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:56,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:56,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:56,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:56,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:57,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:49:58,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:07,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:07,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:07,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:07,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:07,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:07,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:08,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:09,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:18,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:19,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:20,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:20,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:20,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:20,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:20,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:28,722] [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
47%|████▋ | 16/34 [21:45<24:42, 82.34s/it] {'loss': '0.2372', 'grad_norm': '0.4004', 'learning_rate': '7.66e-06', 'ppl': '1.268', 'memory/max_active (GiB)': '92.06', 'memory/max_allocated (GiB)': '92.06', 'memory/device_reserved (GiB)': '92.84', 'tokens/train_per_sec_per_gpu': '112.4', 'tokens/total': 11460928, 'tokens/trainable': 4054932, 'epoch': '2.696'}
47%|████▋ | 16/34 [21:45<24:42, 82.34s/it][2026-04-24 14:50:28,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:28,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:28,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:28,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:28,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:28,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:29,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:30,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:37,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:37,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:37,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:37,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:37,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:38,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:39,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:47,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:48,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:49,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:49,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:57,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:58,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:59,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:59,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:50:59,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:08,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:09,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:10,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:21,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:22,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:30,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:31,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:32,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:40,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:41,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:42,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:42,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:42,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:42,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,242] [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
50%|█████ | 17/34 [23:07<23:15, 82.09s/it] {'loss': '0.2267', 'grad_norm': '0.3525', 'learning_rate': '7.169e-06', 'ppl': '1.255', 'memory/max_active (GiB)': '85.22', 'memory/max_allocated (GiB)': '85.22', 'memory/device_reserved (GiB)': '92.46', 'tokens/train_per_sec_per_gpu': '107.7', 'tokens/total': 12214272, 'tokens/trainable': 4328950, 'epoch': '2.87'}
50%|█████ | 17/34 [23:07<23:15, 82.09s/it][2026-04-24 14:51:50,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:50,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:51,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:52,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:52,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:52,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:52,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:51:52,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:00,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:01,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:07,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:08,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:09,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:10,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:10,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:19,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:20,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:21,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:29,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:30,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:31,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:31,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:31,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:31,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:38,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:39,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:40,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:40,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:40,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:40,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:40,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:52:49,190] [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
53%|█████▎ | 18/34 [24:06<20:02, 75.14s/it] {'loss': '0.2244', 'grad_norm': '0.3431', 'learning_rate': '6.651e-06', 'ppl': '1.252', 'memory/max_active (GiB)': '81.73', 'memory/max_allocated (GiB)': '81.44', 'memory/device_reserved (GiB)': '92.42', 'tokens/train_per_sec_per_gpu': '150.2', 'tokens/total': 12793280, 'tokens/trainable': 4531501, 'epoch': '3'}
53%|█████▎ | 18/34 [24:06<20:02, 75.14s/it][2026-04-24 14:52:53,766] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3/checkpoint-18
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.85s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.85s/it]
[2026-04-24 14:53:26,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:26,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:27,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:28,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:28,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:28,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:35,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:36,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:37,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:46,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:46,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:46,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:46,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:46,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:46,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:47,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:48,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:57,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:58,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:53:59,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:05,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:06,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:07,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:16,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:17,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:18,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:28,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:29,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:30,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:39,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:40,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,073] [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
56%|█████▌ | 19/34 [26:06<22:08, 88.58s/it] {'loss': '0.2119', 'grad_norm': '0.3139', 'learning_rate': '6.113e-06', 'ppl': '1.236', 'memory/max_active (GiB)': '88.17', 'memory/max_allocated (GiB)': '88.17', 'memory/device_reserved (GiB)': '92.42', 'tokens/train_per_sec_per_gpu': '115.2', 'tokens/total': 13588736, 'tokens/trainable': 4825094, 'epoch': '3.174'}
56%|█████▌ | 19/34 [26:06<22:08, 88.58s/it][2026-04-24 14:54:49,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:49,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:50,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:51,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:58,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:58,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:58,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:58,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:58,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:58,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:54:59,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:00,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:09,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:09,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:09,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:09,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:09,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:10,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:11,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:20,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:21,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:22,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:29,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:30,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:31,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:38,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:39,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:46,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:47,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:48,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:53,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:54,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:55,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:55,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:55,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:55,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:55,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:55:55,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:04,825] [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%|█████▉ | 20/34 [27:21<19:46, 84.73s/it] {'loss': '0.2183', 'grad_norm': '0.3137', 'learning_rate': '5.56e-06', 'ppl': '1.244', 'memory/max_active (GiB)': '90.64', 'memory/max_allocated (GiB)': '90.64', 'memory/device_reserved (GiB)': '92.46', 'tokens/train_per_sec_per_gpu': '92.82', 'tokens/total': 14289792, 'tokens/trainable': 5072053, 'epoch': '3.348'}
59%|█████▉ | 20/34 [27:21<19:46, 84.73s/it][2026-04-24 14:56:04,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:04,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:04,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:04,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:05,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:06,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:12,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:13,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:14,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:14,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:14,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:23,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:24,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:25,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:25,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:25,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:32,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:33,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:38,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:39,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:40,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:40,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:40,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:40,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:40,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:40,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:49,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:50,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:51,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:57,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:58,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:56:59,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:09,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:10,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:11,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:21,711] [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
62%|██████▏ | 21/34 [28:38<17:50, 82.37s/it] {'loss': '0.202', 'grad_norm': '0.3235', 'learning_rate': '5e-06', 'ppl': '1.224', 'memory/max_active (GiB)': '89.7', 'memory/max_allocated (GiB)': '89.7', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '119.7', 'tokens/total': 15045248, 'tokens/trainable': 5340952, 'epoch': '3.522'}
62%|██████▏ | 21/34 [28:38<17:50, 82.37s/it][2026-04-24 14:57:21,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:21,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:21,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:21,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:21,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:22,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:23,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:32,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:33,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:34,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:42,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:43,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:48,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:49,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:50,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:58,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:58,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:58,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:57:59,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:00,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:07,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:07,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:07,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:07,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:07,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:08,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:09,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:17,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:18,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:19,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:20,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:20,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:29,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:30,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:31,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:31,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:31,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,460] [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%|██████▍ | 22/34 [29:56<16:11, 80.98s/it] {'loss': '0.2066', 'grad_norm': '0.3212', 'learning_rate': '4.44e-06', 'ppl': '1.23', 'memory/max_active (GiB)': '90.79', 'memory/max_allocated (GiB)': '90.79', 'memory/device_reserved (GiB)': '92.63', 'tokens/train_per_sec_per_gpu': '100.2', 'tokens/total': 15726400, 'tokens/trainable': 5588502, 'epoch': '3.696'}
65%|██████▍ | 22/34 [29:56<16:11, 80.98s/it][2026-04-24 14:58:39,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:39,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:40,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:41,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:41,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:41,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:41,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:41,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:41,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:48,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:49,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:50,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:58:59,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:00,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:01,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:01,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:01,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:01,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:01,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:01,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:09,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:10,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:11,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:11,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:11,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:11,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:11,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:11,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:20,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:20,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:20,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:20,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:20,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:21,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:22,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:30,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:31,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:32,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:40,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:41,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:42,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:42,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:50,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:50,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:50,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:51,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 14:59:52,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:02,999] [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
68%|██████▊ | 23/34 [31:20<14:59, 81.75s/it] {'loss': '0.2014', 'grad_norm': '0.3328', 'learning_rate': '3.887e-06', 'ppl': '1.223', 'memory/max_active (GiB)': '90.41', 'memory/max_allocated (GiB)': '90.41', 'memory/device_reserved (GiB)': '92.48', 'tokens/train_per_sec_per_gpu': '107.5', 'tokens/total': 16459520, 'tokens/trainable': 5839853, 'epoch': '3.87'}
68%|██████▊ | 23/34 [31:20<14:59, 81.75s/it][2026-04-24 15:00:03,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:03,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:04,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:05,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:05,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:05,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:05,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:05,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:14,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:15,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:16,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:24,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:25,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:26,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:33,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:34,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:35,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:46,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:47,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:52,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:52,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:52,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:52,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:53,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:00:54,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:02,596] [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
71%|███████ | 24/34 [32:19<12:31, 75.10s/it] {'loss': '0.1964', 'grad_norm': '0.3253', 'learning_rate': '3.349e-06', 'ppl': '1.217', 'memory/max_active (GiB)': '91.94', 'memory/max_allocated (GiB)': '91.94', 'memory/device_reserved (GiB)': '92.8', 'tokens/train_per_sec_per_gpu': '148.1', 'tokens/total': 17055296, 'tokens/trainable': 6041021, 'epoch': '4'}
71%|███████ | 24/34 [32:19<12:31, 75.10s/it][2026-04-24 15:01:04,858] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3/checkpoint-24
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.27s/it] Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.27s/it]
[2026-04-24 15:01:41,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:42,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:43,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:44,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:53,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:53,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:53,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:53,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:53,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:53,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:54,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:01:55,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:02,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:03,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:04,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:13,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:14,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:15,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:15,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:15,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:15,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:15,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:15,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:24,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:25,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:26,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:35,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:35,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:36,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:37,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:44,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:45,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:46,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:53,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:54,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:02:55,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,174] [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%|███████▎ | 25/34 [34:22<13:24, 89.35s/it] {'loss': '0.1796', 'grad_norm': '0.3083', 'learning_rate': '2.831e-06', 'ppl': '1.197', 'memory/max_active (GiB)': '90.41', 'memory/max_allocated (GiB)': '90.41', 'memory/device_reserved (GiB)': '92.42', 'tokens/train_per_sec_per_gpu': '137.2', 'tokens/total': 17816576, 'tokens/trainable': 6316219, 'epoch': '4.174'}
74%|███████▎ | 25/34 [34:22<13:24, 89.35s/it][2026-04-24 15:03:05,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:05,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:06,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:12,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:12,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:12,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:12,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:13,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:14,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:15,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:15,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:22,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:23,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:24,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:34,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:35,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:41,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:42,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:43,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:50,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:50,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:50,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:50,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:51,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:03:52,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:00,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:01,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:02,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:10,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:10,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:10,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:10,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:10,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:10,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:11,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:12,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:18,733] [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
76%|███████▋ | 26/34 [35:35<11:16, 84.61s/it] {'loss': '0.1971', 'grad_norm': '0.2821', 'learning_rate': '2.34e-06', 'ppl': '1.218', 'memory/max_active (GiB)': '85.45', 'memory/max_allocated (GiB)': '85.45', 'memory/device_reserved (GiB)': '92.47', 'tokens/train_per_sec_per_gpu': '71.45', 'tokens/total': 18522176, 'tokens/trainable': 6558601, 'epoch': '4.348'}
76%|███████▋ | 26/34 [35:35<11:16, 84.61s/it][2026-04-24 15:04:18,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:18,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:18,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:18,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:18,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:18,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:19,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:20,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:26,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:27,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:28,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:36,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:37,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:38,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:47,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:47,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:47,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:47,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:47,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:47,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:48,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:49,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:58,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:04:59,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:00,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:00,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:00,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:08,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:09,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:10,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:10,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:16,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:16,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:16,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:16,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:17,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:18,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:25,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:26,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,379] [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
79%|███████▉ | 27/34 [36:49<09:29, 81.32s/it] {'loss': '0.1996', 'grad_norm': '0.3084', 'learning_rate': '1.883e-06', 'ppl': '1.221', 'memory/max_active (GiB)': '89.23', 'memory/max_allocated (GiB)': '89.23', 'memory/device_reserved (GiB)': '92.47', 'tokens/train_per_sec_per_gpu': '84.28', 'tokens/total': 19178752, 'tokens/trainable': 6805395, 'epoch': '4.522'}
79%|███████▉ | 27/34 [36:49<09:29, 81.32s/it][2026-04-24 15:05:32,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:32,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:33,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:34,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:42,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:43,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:52,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:53,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:54,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:54,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:54,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:54,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:54,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:05:54,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:04,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:04,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:04,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:04,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:05,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:06,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:07,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:15,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:16,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:17,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:17,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:17,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:17,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:17,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:17,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:24,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:24,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:25,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:26,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:36,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:37,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:38,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:38,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:45,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:46,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:47,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,236] [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
82%|████████▏ | 28/34 [38:15<08:16, 82.68s/it] {'loss': '0.1974', 'grad_norm': '0.2663', 'learning_rate': '1.464e-06', 'ppl': '1.218', 'memory/max_active (GiB)': '89.94', 'memory/max_allocated (GiB)': '89.94', 'memory/device_reserved (GiB)': '92.18', 'tokens/train_per_sec_per_gpu': '107.3', 'tokens/total': 19955264, 'tokens/trainable': 7078327, 'epoch': '4.696'}
82%|████████▏ | 28/34 [38:15<08:16, 82.68s/it][2026-04-24 15:06:58,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:58,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:06:59,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:00,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:00,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:00,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:00,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:00,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:08,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:08,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:08,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:08,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:09,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:10,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:11,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:20,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:21,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:22,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:30,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:31,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:32,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:40,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:40,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:40,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:41,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:42,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:51,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:52,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:07:53,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:03,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:04,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:05,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:14,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:15,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:16,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:25,727] [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
85%|████████▌ | 29/34 [39:42<07:00, 84.12s/it] {'loss': '0.1727', 'grad_norm': '0.2642', 'learning_rate': '1.091e-06', 'ppl': '1.189', 'memory/max_active (GiB)': '88.99', 'memory/max_allocated (GiB)': '88.99', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '87.28', 'tokens/total': 20780416, 'tokens/trainable': 7362825, 'epoch': '4.87'}
85%|████████▌ | 29/34 [39:42<07:00, 84.12s/it][2026-04-24 15:08:25,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:25,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:25,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:25,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:26,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:27,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:36,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:37,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:38,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:38,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:38,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:46,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:47,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:55,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:56,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:57,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:57,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:57,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:57,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:08:57,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:05,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:05,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:05,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:05,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:06,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:07,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:15,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:16,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:17,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:09:27,001] [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
88%|████████▊ | 30/34 [40:44<05:09, 77.27s/it] {'loss': '0.1868', 'grad_norm': '0.305', 'learning_rate': '7.664e-07', 'ppl': '1.205', 'memory/max_active (GiB)': '87.12', 'memory/max_allocated (GiB)': '87.12', 'memory/device_reserved (GiB)': '92.42', 'tokens/train_per_sec_per_gpu': '124.5', 'tokens/total': 21324224, 'tokens/trainable': 7546979, 'epoch': '5'}
88%|████████▊ | 30/34 [40:44<05:09, 77.27s/it][2026-04-24 15:09:31,630] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3/checkpoint-30
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.87s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.87s/it]
[2026-04-24 15:10:02,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:02,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:03,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:04,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:10,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:11,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:18,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:19,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:20,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:29,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:30,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:37,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:37,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:37,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:37,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:37,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:37,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:38,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:39,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:47,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:48,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:49,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:49,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:49,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:49,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:49,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:49,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:58,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:58,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:58,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:10:59,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:00,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:01,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:01,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:01,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:01,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:01,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:01,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:12,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:13,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:14,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:14,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:14,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,415] [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
91%|█████████ | 31/34 [42:40<04:27, 89.01s/it] {'loss': '0.1778', 'grad_norm': '0.2547', 'learning_rate': '4.952e-07', 'ppl': '1.195', 'memory/max_active (GiB)': '89.23', 'memory/max_allocated (GiB)': '89.23', 'memory/device_reserved (GiB)': '92.86', 'tokens/train_per_sec_per_gpu': '115.3', 'tokens/total': 22084992, 'tokens/trainable': 7820419, 'epoch': '5.174'}
91%|█████████ | 31/34 [42:40<04:27, 89.01s/it][2026-04-24 15:11:23,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:23,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:24,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:25,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:33,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:33,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:33,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:33,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:33,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:33,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:34,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:35,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:43,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:44,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:45,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:55,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:11:56,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:01,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:01,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:01,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:02,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:03,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:13,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:14,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:15,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:25,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:26,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:27,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:27,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:36,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:37,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:38,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:38,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:38,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:38,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,531] [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
94%|█████████▍| 32/34 [44:03<02:54, 87.24s/it] {'loss': '0.1849', 'grad_norm': '0.2683', 'learning_rate': '2.806e-07', 'ppl': '1.203', 'memory/max_active (GiB)': '83.19', 'memory/max_allocated (GiB)': '83.19', 'memory/device_reserved (GiB)': '92.4', 'tokens/train_per_sec_per_gpu': '107.7', 'tokens/total': 22829568, 'tokens/trainable': 8083931, 'epoch': '5.348'}
94%|█████████▍| 32/34 [44:03<02:54, 87.24s/it][2026-04-24 15:12:46,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:46,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:47,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:48,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:58,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:12:59,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:00,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:00,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:00,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:00,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:00,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:09,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:10,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:19,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:20,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:21,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:28,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:28,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:28,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:28,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:28,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:28,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:29,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:30,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:37,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:38,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:39,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:47,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:48,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:55,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:56,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:13:57,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,573] [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
97%|█████████▋| 33/34 [45:22<01:24, 84.78s/it] {'loss': '0.1889', 'grad_norm': '0.2613', 'learning_rate': '1.254e-07', 'ppl': '1.208', 'memory/max_active (GiB)': '82.5', 'memory/max_allocated (GiB)': '82.5', 'memory/device_reserved (GiB)': '92.34', 'tokens/train_per_sec_per_gpu': '91.68', 'tokens/total': 23536576, 'tokens/trainable': 8332593, 'epoch': '5.522'}
97%|█████████▋| 33/34 [45:22<01:24, 84.78s/it][2026-04-24 15:14:05,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:05,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:06,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:07,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:15,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:16,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:25,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:25,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:25,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:26,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:27,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:37,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:38,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:39,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:39,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:46,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:47,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:48,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:48,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:48,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:48,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:48,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:56,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:56,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:57,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:58,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:59,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:14:59,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:08,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:09,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:10,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:10,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:10,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:10,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:10,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:10,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:18,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:18,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:18,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:19,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:20,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1476492] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-24 15:15:27,341] [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
100%|██████████| 34/34 [46:44<00:00, 83.88s/it] {'loss': '0.1773', 'grad_norm': '0.245', 'learning_rate': '3.144e-08', 'ppl': '1.194', 'memory/max_active (GiB)': '91.71', 'memory/max_allocated (GiB)': '91.71', 'memory/device_reserved (GiB)': '92.82', 'tokens/train_per_sec_per_gpu': '90.63', 'tokens/total': 24326720, 'tokens/trainable': 8610182, 'epoch': '5.696'}
100%|██████████| 34/34 [46:44<00:00, 83.88s/it][2026-04-24 15:15:29,687] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3/checkpoint-34
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.09s/it] Writing model shards: 100%|██████████| 1/1 [00:07<00:00, 7.10s/it]
{'train_runtime': '2840', 'train_samples_per_second': '0.383', 'train_steps_per_second': '0.012', 'train_loss': '0.2681', 'memory/max_active (GiB)': '31.77', 'memory/max_allocated (GiB)': '31.77', 'memory/device_reserved (GiB)': '90.79', 'epoch': '5.696', 'tokens/train_per_sec_per_gpu': '0'}
100%|██████████| 34/34 [47:20<00:00, 83.88s/it] 100%|██████████| 34/34 [47:20<00:00, 83.54s/it]
[2026-04-24 15:16:04,035] [INFO] [axolotl.train.save_trained_model:241] [PID:1476492] Training completed! Saving trained model to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3.
[2026-04-24 15:16:05,937] [INFO] [axolotl.core.trainers.base._save:741] [PID:1476492] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.96s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.96s/it]
[2026-04-24 15:16:13,143] [INFO] [axolotl.train.save_trained_model:355] [PID:1476492] Model successfully saved to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-316-axolotl__Qwen3-8B-v3