Files
CoderForge-Preview-v3-316-a…/debug.log
ModelHub XC 5fb5410cc3 初始化项目,由ModelHub XC社区提供模型
Model: laion/CoderForge-Preview-v3-316-axolotl__Qwen3-8B
Source: Original Platform
2026-05-03 03:14:21 +08:00

2798 lines
431 KiB
Plaintext
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

[2026-04-23 08:56:21,780] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:916134] bf16 support detected, enabling for this configuration.
[2026-04-23 08:56:21,837] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:916134] baseline 0.000GB ()
[2026-04-23 08:56:21,837] [INFO] [axolotl.cli.config.load_cfg:341] [PID:916134] config:
{
"activation_offloading": true,
"adam_beta1": 0.9,
"adam_beta2": 0.95,
"axolotl_config_path": "/e/scratch/jureap59/feuer1/code/axolotl_configs/qwen3_8b_cf_v3_316.yaml",
"base_model": "Qwen/Qwen3-8B",
"base_model_config": "Qwen/Qwen3-8B",
"batch_size": 32,
"bf16": true,
"capabilities": {
"bf16": true,
"compute_capability": "sm_90",
"fp8": true,
"n_gpu": 4,
"n_node": 1,
"tf32": true
},
"chat_template": "chatml",
"context_parallel_size": 1,
"dataloader_num_workers": 4,
"dataloader_pin_memory": true,
"dataloader_prefetch_factor": 256,
"dataset_num_proc": 288,
"dataset_prepared_path": "/e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/cf-v3-316",
"datasets": [
{
"ds_type": "parquet",
"message_property_mappings": {
"content": "content",
"role": "role"
},
"path": "laion/CoderForge-Preview-v3-316",
"trust_remote_code": false
}
],
"ddp": true,
"deepspeed": {
"bf16": {
"enabled": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false,
"zero_optimization": {
"contiguous_gradients": true,
"gather_16bit_weights_on_model_save": true,
"max_live_parameters": 0,
"max_reuse_distance": 0,
"overlap_comm": true,
"reduce_bucket_size": "auto",
"stage": 3,
"stage3_param_persistence_threshold": "auto",
"stage3_prefetch_bucket_size": "auto",
"sub_group_size": 0
}
},
"device": "cuda:0",
"device_map": {
"": 0
},
"dion_rank_fraction": 1.0,
"dion_rank_multiple_of": 1,
"eaft_alpha": 1.0,
"eaft_k": 20,
"env_capabilities": {
"torch_version": "2.9.1"
},
"eval_batch_size": 1,
"eval_causal_lm_metrics": [
"sacrebleu",
"comet",
"ter",
"chrf"
],
"eval_max_new_tokens": 128,
"eval_table_size": 0,
"evals_per_epoch": 0,
"experimental_skip_move_to_device": true,
"flash_attention": true,
"fp16": false,
"generate_samples": false,
"generation_do_sample": true,
"generation_max_new_tokens": 50,
"generation_prompt_ratio": 0.5,
"generation_temperature": 0.7,
"gradient_accumulation_steps": 8,
"gradient_checkpointing": true,
"gradient_checkpointing_kwargs": {
"use_reentrant": true
},
"include_tkps": true,
"layer_offloading": false,
"learning_rate": 1e-05,
"lisa_layers_attribute": "model.layers",
"load_best_model_at_end": false,
"load_in_4bit": false,
"load_in_8bit": false,
"local_rank": 0,
"logging_steps": 1,
"lora_dropout": 0.0,
"loraplus_lr_embedding": 1e-06,
"loss_watchdog_patience": 3,
"loss_watchdog_threshold": 5.0,
"lr_scheduler": "cosine",
"max_grad_norm": 1.0,
"mean_resizing_embeddings": false,
"merge_method": "memory_efficient",
"micro_batch_size": 1,
"model_config_type": "qwen3",
"num_epochs": 3.0,
"num_generation_samples": 3,
"optimizer": "adamw_torch",
"otel_metrics_host": "localhost",
"otel_metrics_port": 8000,
"output_dir": "/e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B",
"pretrain_multipack_attn": true,
"profiler_steps_start": 0,
"qlora_sharded_model_loading": false,
"quantize_moe_experts": false,
"ray_num_workers": 1,
"resources_per_worker": {
"GPU": 1
},
"sample_packing_bin_size": 200,
"sample_packing_group_size": 100000,
"save_only_model": false,
"save_safetensors": true,
"save_strategy": "epoch",
"sequence_len": 32768,
"shuffle_before_merging_datasets": false,
"shuffle_merged_datasets": true,
"skip_prepare_dataset": false,
"streaming_multipack_buffer_size": 10000,
"strict": false,
"tensor_parallel_size": 1,
"tf32": false,
"tiled_mlp_use_original_mlp": true,
"tokenizer_config": "Qwen/Qwen3-8B",
"tokenizer_save_jinja_files": true,
"torch_dtype": "torch.bfloat16",
"train_on_inputs": false,
"trl": {
"async_prefetch": false,
"log_completions": false,
"mask_truncated_completions": false,
"ref_model_mixup_alpha": 0.9,
"ref_model_sync_steps": 64,
"replay_buffer_size": 0,
"replay_recompute_logps": true,
"reroll_max_groups": 1,
"reroll_start_fraction": 1.0,
"reward_num_workers": 1,
"scale_rewards": true,
"skip_zero_advantage_batches": true,
"sync_ref_model": false,
"use_data_producer": false,
"use_vllm": false,
"vllm_lora_sync": false,
"vllm_server_host": "0.0.0.0",
"vllm_server_port": 8000
},
"use_otel_metrics": false,
"use_ray": false,
"val_set_size": 0.0,
"vllm": {
"device": "auto",
"dtype": "auto",
"gpu_memory_utilization": 0.9,
"host": "0.0.0.0",
"port": 8000
},
"wandb_name": "cf-v3-316-axolotl__Qwen3-8B",
"warmup_ratio": 0.1875,
"weight_decay": 0.01,
"world_size": 4
}
[2026-04-23 08:56:21,865] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:916134] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.
[2026-04-23 08:56:22,372] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:916134] EOS: 151645 / <|im_end|>
[2026-04-23 08:56:22,373] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:916134] BOS: None / None
[2026-04-23 08:56:22,373] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:916134] PAD: 151643 / <|endoftext|>
[2026-04-23 08:56:22,373] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:916134] UNK: None / None
[2026-04-23 08:56:22,572] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:916134] Loading prepared dataset from disk at /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/cf-v3-316/89dcaefec5108222b90555ccb5a9ef73...
[2026-04-23 08:56:22,579] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:916134] total_num_tokens: 2_531_370
[2026-04-23 08:56:22,583] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:916134] `total_supervised_tokens: 567_197`
[2026-04-23 08:56:22,583] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:916134] total_num_steps: 9
[2026-04-23 08:56:22,583] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:916134] Maximum number of steps set at 9
[2026-04-23 08:56:22,620] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:916134] loading tokenizer... Qwen/Qwen3-8B
[2026-04-23 08:56:22,880] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:916134] EOS: 151645 / <|im_end|>
[2026-04-23 08:56:22,881] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:916134] BOS: None / None
[2026-04-23 08:56:22,881] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:916134] PAD: 151643 / <|endoftext|>
[2026-04-23 08:56:22,881] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:916134] UNK: None / None
[2026-04-23 08:56:22,881] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:916134] Loading model
[2026-04-23 08:56:22,923] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:916134] Patched Trainer.evaluation_loop with nanmean loss calculation
[2026-04-23 08:56:22,924] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:916134] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
[2026-04-23 08:56:23,172] [INFO] [axolotl.monkeypatch.attention.flash_attn_4.patch_flash_attn_4:52] [PID:916134] Flash Attention 4 is available for your GPU and offers faster training speeds. To enable: pip install flash-attn-4
[2026-04-23 08:56:23,173] [INFO] [axolotl.monkeypatch.deepspeed_utils.patch_checkpoint_wrapper_setattr:52] [PID:916134] CheckpointWrapper patched to forward DeepSpeed attributes
[2026-04-23 08:56:54,302] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:916134] Converting modules to torch.bfloat16
[2026-04-23 08:56:54,305] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:916134] Memory usage after model load 4.973GB (+4.973GB allocated, +5.080GB reserved)
[2026-04-23 08:57:00,717] [INFO] [axolotl.train.save_initial_configs:421] [PID:916134] Pre-saving tokenizer to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B...
[2026-04-23 08:57:00,850] [INFO] [axolotl.train.save_initial_configs:426] [PID:916134] Pre-saving model config to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B...
[2026-04-23 08:57:00,853] [INFO] [axolotl.train.execute_training:222] [PID:916134] Starting trainer...
[2026-04-23 08:57:01,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:01,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_id to wrapped module Qwen3DecoderLayer
0%| | 0/9 [00:00<?, ?it/s][2026-04-23 08:57:03,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:03,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:04,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:05,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:06,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:06,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:15,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:16,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:17,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:17,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:17,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:17,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:17,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:17,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:27,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:27,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:28,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:29,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:30,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:30,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:42,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:43,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:44,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:52,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:52,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:52,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:52,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:52,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:53,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:57:54,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:06,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:07,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:08,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:16,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:16,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:16,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:17,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:18,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:19,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:19,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:27,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:28,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:29,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:30,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:30,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:30,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:30,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:30,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
11%|█ | 1/9 [01:36<12:52, 96.52s/it]
{'loss': '0.8329', 'grad_norm': '15.89', 'learning_rate': '0', 'ppl': '2.3', 'memory/max_active (GiB)': '76.51', 'memory/max_allocated (GiB)': '75.03', 'memory/device_reserved (GiB)': '88.49', 'tokens/train_per_sec_per_gpu': '64.81', 'tokens/total': 847616, 'tokens/trainable': 189135, 'epoch': '0.3478'}
11%|█ | 1/9 [01:36<12:52, 96.52s/it][2026-04-23 08:58:38,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:38,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:38,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:39,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:40,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:41,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:49,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:49,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:49,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:49,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:50,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:58:51,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:01,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:02,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:03,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:15,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:15,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:16,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:17,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:18,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:18,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:18,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:28,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:29,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:30,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:40,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:41,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:42,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:51,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:52,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 08:59:53,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:02,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:03,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:04,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:04,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:04,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:04,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:04,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:04,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:12,692] [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
22%|██▏ | 2/9 [03:10<11:04, 94.94s/it]
{'loss': '0.8281', 'grad_norm': '15.8', 'learning_rate': '5e-06', 'ppl': '2.289', 'memory/max_active (GiB)': '90.29', 'memory/max_allocated (GiB)': '90.29', 'memory/device_reserved (GiB)': '92.42', 'tokens/train_per_sec_per_gpu': '58.1', 'tokens/total': 1729344, 'tokens/trainable': 386305, 'epoch': '0.6957'}
22%|██▏ | 2/9 [03:10<11:04, 94.94s/it][2026-04-23 09:00:12,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:12,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:12,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:13,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:14,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:15,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:26,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:27,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:28,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:39,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:40,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:41,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:41,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:41,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:41,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:41,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:41,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:50,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:50,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:51,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:52,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:00:53,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:03,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:04,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:05,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:15,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:16,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:17,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:26,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:27,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:28,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:28,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:01:37,851] [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
33%|███▎ | 3/9 [04:35<09:02, 90.47s/it]
{'loss': '0.7065', 'grad_norm': '9.597', 'learning_rate': '1e-05', 'ppl': '2.027', 'memory/max_active (GiB)': '88.28', 'memory/max_allocated (GiB)': '88.28', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '68.42', 'tokens/total': 2534464, 'tokens/trainable': 567197, 'epoch': '1'}
33%|███▎ | 3/9 [04:35<09:02, 90.47s/it][2026-04-23 09:01:41,941] [INFO] [axolotl.core.trainers.base._save:741] [PID:916134] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B/checkpoint-3
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.76s/it]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.76s/it]
[2026-04-23 09:02:09,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:09,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:10,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:11,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:11,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:11,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:20,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:21,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:22,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:32,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:33,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:34,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:42,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:43,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:44,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:44,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:44,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:44,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:44,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:44,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:54,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:55,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:56,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:57,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:57,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:02:57,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:07,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:08,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:15,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:16,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:17,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:17,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:17,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:17,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:17,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:25,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:26,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:27,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:37,977] [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
44%|████▍ | 4/9 [06:35<08:30, 102.18s/it]
{'loss': '0.555', 'grad_norm': '7.088', 'learning_rate': '9.505e-06', 'ppl': '1.742', 'memory/max_active (GiB)': '91.23', 'memory/max_allocated (GiB)': '91.23', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '73.5', 'tokens/total': 3410048, 'tokens/trainable': 761742, 'epoch': '1.348'}
44%|████▍ | 4/9 [06:35<08:30, 102.18s/it][2026-04-23 09:03:38,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:38,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:39,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:40,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:40,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:40,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:40,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:49,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:49,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:50,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:51,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:52,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:52,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:52,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:52,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:03:52,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:03,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:04,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:05,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:13,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:14,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:15,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:24,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:24,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:25,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:26,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:27,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:27,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:27,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:36,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:37,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:38,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:38,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:38,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:38,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:38,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:38,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:47,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:48,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:49,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:59,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:04:59,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:00,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:01,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:02,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,133] [WARNING] [stage3.py:2497:step] 12 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%|█████▌ | 5/9 [08:10<06:38, 99.65s/it]
{'loss': '0.4561', 'grad_norm': '1.787', 'learning_rate': '8.117e-06', 'ppl': '1.578', 'memory/max_active (GiB)': '91', 'memory/max_allocated (GiB)': '91', 'memory/device_reserved (GiB)': '92.73', 'tokens/train_per_sec_per_gpu': '66.86', 'tokens/total': 4309696, 'tokens/trainable': 962414, 'epoch': '1.696'}
56%|█████▌ | 5/9 [08:10<06:38, 99.65s/it][2026-04-23 09:05:13,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:13,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:14,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:15,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:15,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:15,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:15,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:15,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:23,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:23,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:23,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:24,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:25,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:34,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:35,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:36,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:46,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:47,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:48,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:05:59,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:00,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:01,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:08,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:08,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:08,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:08,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:08,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:09,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:10,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:20,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:21,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:22,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:22,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:06:31,791] [WARNING] [stage3.py:2497:step] 4 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
67%|██████▋ | 6/9 [09:29<04:37, 92.51s/it]
{'loss': '0.4101', 'grad_norm': '1.196', 'learning_rate': '6.113e-06', 'ppl': '1.507', 'memory/max_active (GiB)': '83.8', 'memory/max_allocated (GiB)': '83.8', 'memory/device_reserved (GiB)': '92.73', 'tokens/train_per_sec_per_gpu': '77.05', 'tokens/total': 5068928, 'tokens/trainable': 1134394, 'epoch': '2'}
67%|██████▋ | 6/9 [09:29<04:37, 92.51s/it][2026-04-23 09:06:33,187] [INFO] [axolotl.core.trainers.base._save:741] [PID:916134] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B/checkpoint-6
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.00s/it]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.00s/it]
[2026-04-23 09:07:02,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:02,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:03,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:04,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:05,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:05,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:05,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:05,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:14,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:15,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:16,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:16,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:16,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:16,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:25,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:25,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:25,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:25,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:25,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:26,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:27,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:38,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:39,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:40,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:40,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:40,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:40,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:50,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:50,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:50,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:50,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:50,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:51,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:07:52,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:02,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:03,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:04,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:13,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:14,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:15,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:15,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:23,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:24,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:25,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:32,789] [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
78%|███████▊ | 7/9 [11:30<03:23, 101.82s/it]
{'loss': '0.383', 'grad_norm': '0.9671', 'learning_rate': '3.887e-06', 'ppl': '1.467', 'memory/max_active (GiB)': '90.29', 'memory/max_allocated (GiB)': '90.29', 'memory/device_reserved (GiB)': '92.38', 'tokens/train_per_sec_per_gpu': '61.84', 'tokens/total': 5937728, 'tokens/trainable': 1333382, 'epoch': '2.348'}
78%|███████▊ | 7/9 [11:30<03:23, 101.82s/it][2026-04-23 09:08:32,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:32,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:32,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:32,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:33,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:34,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:43,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:44,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:45,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:55,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:56,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:08:57,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:08,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:09,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:10,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:10,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:10,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:10,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:10,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:10,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:20,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:21,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:22,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:22,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:22,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:22,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:22,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:22,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:30,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:30,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:30,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:31,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:32,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:33,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:42,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:43,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:44,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:53,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:53,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:53,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:53,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:54,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:55,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:09:56,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,444] [WARNING] [stage3.py:2497:step] 7 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
89%|████████▉ | 8/9 [13:04<01:39, 99.22s/it]
{'loss': '0.3792', 'grad_norm': '0.8572', 'learning_rate': '1.883e-06', 'ppl': '1.461', 'memory/max_active (GiB)': '90.17', 'memory/max_allocated (GiB)': '90.17', 'memory/device_reserved (GiB)': '92.36', 'tokens/train_per_sec_per_gpu': '57.71', 'tokens/total': 6802944, 'tokens/trainable': 1526338, 'epoch': '2.696'}
89%|████████▉ | 8/9 [13:04<01:39, 99.22s/it][2026-04-23 09:10:06,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:06,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:07,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:08,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:17,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:18,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:19,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:19,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:19,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:28,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:28,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:28,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:28,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:29,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:30,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:40,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:40,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:40,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:40,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:41,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:42,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:53,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:53,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:53,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:53,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:53,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:54,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:55,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:10:56,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:05,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:05,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:05,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:05,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:06,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:07,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:17,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:17,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:17,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:18,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:19,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:20,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:20,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:916134] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-23 09:11:30,596] [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
100%|██████████| 9/9 [14:28<00:00, 94.51s/it]
{'loss': '0.3929', 'grad_norm': '0.7735', 'learning_rate': '4.952e-07', 'ppl': '1.481', 'memory/max_active (GiB)': '90.77', 'memory/max_allocated (GiB)': '90.77', 'memory/device_reserved (GiB)': '92.49', 'tokens/train_per_sec_per_gpu': '69.83', 'tokens/total': 7603392, 'tokens/trainable': 1701591, 'epoch': '3'}
100%|██████████| 9/9 [14:28<00:00, 94.51s/it][2026-04-23 09:11:33,374] [INFO] [axolotl.core.trainers.base._save:741] [PID:916134] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B/checkpoint-9
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:05<00:00, 5.72s/it]
Writing model shards: 100%|██████████| 1/1 [00:05<00:00, 5.72s/it]
{'train_runtime': '892.4', 'train_samples_per_second': '0.323', 'train_steps_per_second': '0.01', 'train_loss': '0.5493', 'memory/max_active (GiB)': '31.77', 'memory/max_allocated (GiB)': '31.77', 'memory/device_reserved (GiB)': '92.49', 'epoch': '3', 'tokens/train_per_sec_per_gpu': '0'}
100%|██████████| 9/9 [14:52<00:00, 94.51s/it]
100%|██████████| 9/9 [14:52<00:00, 99.15s/it]
[2026-04-23 09:11:55,574] [INFO] [axolotl.train.save_trained_model:241] [PID:916134] Training completed! Saving trained model to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B.
[2026-04-23 09:11:56,968] [INFO] [axolotl.core.trainers.base._save:741] [PID:916134] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:05<00:00, 5.94s/it]
Writing model shards: 100%|██████████| 1/1 [00:05<00:00, 5.94s/it]
[2026-04-23 09:12:03,086] [INFO] [axolotl.train.save_trained_model:355] [PID:916134] Model successfully saved to /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B